POSTER-1: What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

Keywords: Uncertainty Explaination Uncertainty Quantification Interpretability

Scores: [ 6 6 6 6 ]

Uncertainty quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples, however, it is often unclear what exactly these methods identify. In this work, we propose a framework for categorizing uncertain examples flagged by UQ methods. We introduce the confusion density matrix---a kernel-based approximation of the misclassification density---and use this to categorize suspicious examples identified by a given uncertainty method into three classes: out-of-distribution (OOD) examples, boundary (Bnd) examples, and examples in regions of high in-distribution misclassification (IDM). Through extensive experiments, we show that our framework provides a new and distinct perspective for assessing differences between uncertainty quantification methods, thereby forming a valuable assessment benchmark.

POSTER-2: Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy

Keywords: shortcut learning spurious correlations perfect stable feature perception tasks implicit bias in optimization improving inductive biases

Scores: [ 6 5 6 6 ]

Common explanations for shortcut learning assume that the shortcut improves prediction only under the training distribution. Thus, models trained in the typical way by minimizing log-loss using gradient descent, which we call default-ERM, should utilize the shortcut. However, even when the stable feature determines the label in the training distribution and the shortcut does not provide any additional information, like in perception tasks, default-ERM exhibits shortcut learning. Why are such solutions preferred when the loss can be driven to zero when using the stable feature alone? By studying a linear perception task, we show that default-ERM’s preference for maximizing the margin, even without overparameterization, leads to models that depend more on the shortcut than the stable feature. This insight suggests that default-ERM’s implicit inductive bias towards max-margin may be unsuitable for perception tasks. Instead, we consider inductive biases toward uniform margins. We show that uniform margins guarantee sole dependence on the perfect stable feature in the linear perception task and suggest alternative loss functions, termed margin control (MARG-CTRL), that encourage uniform-margin solutions. MARG-CTRL techniques mitigate shortcut learning on a variety of vision and language tasks, showing that changing inductive biases can remove the need for complicated shortcut-mitigating methods in perception tasks.

POSTER-3: Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

Keywords: robust pre-training adversarial contrastive learning

Scores: [ 8 6 6 4 ]

Adversarial contrastive learning (ACL) is a technique that enhances standard contrastive learning (SCL) by incorporating adversarial data to learn a robust representation that can withstand adversarial attacks and common corruptions without requiring costly annotations. To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation. However, it is unclear how the style-independence property benefits ACL-learned robust representations. In this paper, we leverage the technique of causal reasoning to interpret the ACL and propose adversarial invariant regularization (AIR) to enforce independence from style factors. We regulate the ACL using both SIR and AIR to output the robust representation. Theoretically, we show that AIR implicitly encourages the representational distance between different views of natural data and their adversarial variants to be independent of style factors. Empirically, our experimental results show that invariant regularization significantly improves the performance of state-of-the-art ACL methods in terms of both standard generalization and robustness on downstream tasks. To the best of our knowledge, we are the first to apply causal reasoning to interpret ACL and develop AIR for enhancing ACL-learned robust representations. Our source code is at

POSTER-4: An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions

Keywords: Role Extraction Graph Learning Node Embeddings Weisfeiler Lehman Equitable Partition

Scores: [ 5 5 6 6 ]

POSTER-5: Generator Identification for Linear SDEs with Additive and Multiplicative Noise

Keywords: Linear SDE Identification Causal inference

Scores: [ 7 4 4 5 4 7 ]

In this paper, we present conditions for identifying the generator of a linear stochastic differential equation (SDE) from the distribution of its solution process with a given fixed initial state. These identifiability conditions are crucial in causal inference using linear SDEs as they enable the identification of the post-intervention distributions from its observational distribution. Specifically, we derive a sufficient and necessary condition for identifying the generator of linear SDEs with additive noise, as well as a sufficient condition for identifying the generator of linear SDEs with multiplicative noise. We show that the conditions derived for both types of SDEs are generic. Moreover, we offer geometric interpretations of the derived identifiability conditions to enhance their understanding. To validate our theoretical results, we perform a series of simulations, which support and substantiate the established findings.

POSTER-6: Algorithm Selection for Deep Active Learning with Imbalanced Datasets

Keywords: Deep Learning Active Learning

Scores: [ 7 6 6 5 3 ]

Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning algorithms can vary dramatically across datasets and applications. It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning. For any unlabeled dataset, our (meta) algorithm TAILOR (Thompson ActIve Learning algORithm selection) iteratively and adaptively chooses among a set of candidate active learning algorithms. TAILOR uses novel reward functions aimed at gathering class-balanced examples. Extensive experiments in multi-class and multi-label applications demonstrate TAILOR's effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms. Our implementation of TAILOR is open-sourced at

POSTER-7: Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

Keywords: open-world semi-supervised learning; novel class discovery;

Scores: [ 5 6 5 5 ]

Open-world Semi-Supervised Learning (OSSL) is a realistic and challenging task, aiming to classify unlabeled samples from both seen and novel classes using partially labeled samples from the seen classes. Previous works typically explore the relationship of samples as priors on the pre-defined single-granularity labels to help novel class recognition. In fact, classes follow a taxonomy and samples can be classified at multiple levels of granularity, which contains more underlying relationships for supervision. We thus argue that learning with single-granularity labels results in sub-optimal representation learning and inaccurate pseudo labels, especially with unknown classes. In this paper, we take the initiative to explore and propose a uniformed framework, called Taxonomic context prIors Discovering and Aligning (TIDA), which exploits the relationship of samples under various granularity. It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i.e., sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels.Specifically, TIDA comprises two components: i) A taxonomic context discovery module that constructs a set of hierarchical prototypes in the latent space to discover the underlying taxonomic context priors; ii) A taxonomic context-based prediction alignment module that enforces consistency across hierarchical predictions to build the reliable relationship between classes among various granularity and provide additions supervision. We demonstrate that these two components are mutually beneficial for an effective OSSL framework, which is theoretically explained from the perspective of the EM algorithm. Extensive experiments on seven commonly used datasets show that TIDA can significantly improve the performance and achieve a new state of the art. The source codes are publicly available at

POSTER-8: Learning Invariant Representations of Graph Neural Networks via Cluster Generalization

Keywords: Graph neural networks network representation learning deep learning

Scores: [ 4 6 7 7 7 ]

POSTER-9: The expressive power of pooling in Graph Neural Networks

Keywords: Graph Neural Networks Graph pooling Expressive power

Scores: [ 6 7 6 6 4 ]

In Graph Neural Networks (GNNs), hierarchical pooling operators generate local summaries of the data by coarsening the graph structure and the vertex features. Considerable attention has been devoted to analyzing the expressive power of message-passing (MP) layers in GNNs, while a study on how graph pooling affects the expressiveness of a GNN is still lacking. Additionally, despite the recent advances in the design of pooling operators, there is not a principled criterion to compare them. In this work, we derive sufficient conditions for a pooling operator to fully preserve the expressive power of the MP layers before it. These conditions serve as a universal and theoretically-grounded criterion for choosing among existing pooling operators or designing new ones. Based on our theoretical findings, we analyze several existing pooling operators and identify those that fail to satisfy the expressiveness conditions. Finally, we introduce an experimental setup to verify empirically the expressive power of a GNN equipped with pooling layers, in terms of its capability to perform a graph isomorphism test.

POSTER-10: Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Keywords: Backdoor Attack Trustworthy AI Backdoor Learning

Scores: [ 6 4 3 5 ]

Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which predicts poisoned samples with particular triggers to particular target classes, while behaving normally on benign samples. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk, which mainly captures the risk on the shared adversarial examples (SAEs) between the backdoored model and the purified model. This upper bound further suggests a novel bi-level optimization problem for mitigating backdoor using adversarial training techniques. To solve it, we propose Shared Adversarial Unlearning (SAU). Specifically, SAU first generates SAEs, and then, unlearns the generated SAEs such that they are either correctly classified by the purified model and/or differently classified by the two models, such that the backdoor effect in the backdoored model will be mitigated in the purified model. Experiments on various benchmark datasets and network architectures show that our proposed method achieves state-of-the-art performance for backdoor defense. The code is available at (PyTorch) and (MindSpore).

POSTER-11: The Crucial Role of Normalization in Sharpness-Aware Minimization

Keywords: Sharpness-Aware Minimization Normalization Deep Learning Theory

Scores: [ 5 5 6 7 7 ]

Sharpness-Aware Minimization (SAM) is a recently proposed gradient-based optimizer (Foret et al., ICLR 2021) that greatly improves the prediction performance of deep neural networks. Consequently, there has been a surge of interest in explaining its empirical success. We focus, in particular, on understanding the role played by normalization, a key component of the SAM updates. We theoretically and empirically study the effect of normalization in SAM for both convex and non-convex functions, revealing two key roles played by normalization: i) it helps in stabilizing the algorithm; and ii) it enables the algorithm to drift along a continuum (manifold) of minima -- a property identified by recent theoretical works that is the key to better performance. We further argue that these two properties of normalization make SAM robust against the choice of hyper-parameters, supporting the practicality of SAM. Our conclusions are backed by various experiments.

POSTER-12: Towards Personalized Federated Learning via Heterogeneous Model Reassembly

Keywords: Federated Learning

Scores: [ 5 6 8 7 ]

This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneous model reassembly to achieve personalized federated learning. In particular, we approach the problem of heterogeneous model personalization as a model-matching optimization task on the server side. Moreover, pFedHR automatically and dynamically generates informative and diverse personalized candidates with minimal human intervention. Furthermore, our proposed heterogeneous model reassembly technique mitigates the adverse impact introduced by using public data with different distributions from the client data to a certain extent. Experimental results demonstrate that pFedHR outperforms baselines on three datasets under both IID and Non-IID settings. Additionally, pFedHR effectively reduces the adverse impact of using different public data and dynamically generates diverse personalized models in an automated manner.

POSTER-13: Active Learning for Semantic Segmentation with Multi-class Label Query

Keywords: semantic segmentation; active learning; partial label learning

Scores: [ 7 5 5 6 ]

This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (\(\textit{e.g.}\), superpixels), and for each of such regions, asks an oracle for a multi-hot vector indicating all classes existing in the region. This multi-class labeling strategy is substantially more efficient than existing ones like segmentation, polygon, and even dominant class labeling in terms of annotation time per click. However, it introduces the class ambiguity issue in training as it assigns partial labels (\(\textit{i.e.}\), a set of candidate classes) to individual pixels. We thus propose a new algorithm for learning semantic segmentation while disambiguating the partial labels in two stages. In the first stage, it trains a segmentation model directly with the partial labels through two new loss functions motivated by partial label learning and multiple instance learning. In the second stage, it disambiguates the partial labels by generating pixel-wise pseudo labels, which are used for supervised learning of the model. Equipped with a new acquisition function dedicated to the multi-class labeling, our method outperforms previous work on Cityscapes and PASCAL VOC 2012 while spending less annotation cost. Our code and results are available at

POSTER-14: Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value

Keywords: Convex Optimization Acceleration First-Order methods

Scores: [ 9 7 5 8 4 ]

In convex optimization, first-order optimization methods efficiently minimizing function values have been a central subject study since Nesterov's seminal work of 1983. Recently, however, Kim and Fessler's OGM-G and Lee et al.'s FISTA-G have been presented as alternatives that efficiently minimize the gradient magnitude instead. In this paper, we present H-duality, which represents a surprising one-to-one correspondence between methods efficiently minimizing function values and methods efficiently minimizing gradient magnitude. In continuous-time formulations, H-duality corresponds to reversing the time dependence of the dissipation/friction term. To the best of our knowledge, H-duality is different from Lagrange/Fenchel duality and is distinct from any previously known duality or symmetry relations. Using H-duality, we obtain a clearer understanding of the symmetry between Nesterov's method and OGM-G, derive a new class of methods efficiently reducing gradient magnitudes of smooth convex functions, and find a new composite minimization method that is simpler and faster than FISTA-G.

POSTER-15: Optimizing over trained GNNs via symmetry breaking

Keywords: Mixed-integer optimization Graph neural network Symmetry-breaking Molecular design

Scores: [ 6 7 7 7 ]

Optimization over trained machine learning models has applications including: verification, minimizing neural acquisition functions, and integrating a trained surrogate into a larger decision-making problem. This paper formulates and solves optimization problems constrained by trained graph neural networks (GNNs). To circumvent the symmetry issue caused by graph isomorphism, we propose two types of symmetry-breaking constraints: one indexing a node 0 and one indexing the remaining nodes by lexicographically ordering their neighbor sets. To guarantee that adding these constraints will not remove all symmetric solutions, we construct a graph indexing algorithm and prove that the resulting graph indexing satisfies the proposed symmetry-breaking constraints. For the classical GNN architectures considered in this paper, optimizing over a GNN with a fixed graph is equivalent to optimizing over a dense neural network. Thus, we study the case where the input graph is not fixed, implying that each edge is a decision variable, and develop two mixed-integer optimization formulations. To test our symmetry-breaking strategies and optimization formulations, we consider an application in molecular design.

POSTER-16: An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

Keywords: Bilevel optimization nonconvex constrained optimization convergence analysis

Scores: [ 3 7 5 5 ]

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for the considered bilevel problems, which generalizes the existing metric, for a nonconvex lower-level objective that satisfies the Polyak-Łojasiewicz (PL) condition. We then propose a Generalized ALternating mEthod for bilevel opTimization (GALET) tailored to BLO with convex PL LL problem and establish that GALET achieves an \(\epsilon\)-stationary point for the considered problem within \(\tilde{\cal O}(\epsilon^{-1})\) iterations, which matches the iteration complexity of GD for single-level smooth nonconvex problems.

POSTER-17: Scalable Fair Influence Maximization

Keywords: influence maximization approximation algorithm social fairness

Scores: [ 6 6 6 3 ]

Given a graph \(G\), a community structure \(\mathcal{C}\), and a budget \(k\), the fair influence maximization problem aims to select a seed set \(S\) (\(|S|\leq k\)) that maximizes the influence spread while narrowing the influence gap between different communities. While various fairness notions exist, the welfare fairness notion, which balances fairness level and influence spread, has shown promising effectiveness. However, the lack of efficient algorithms for optimizing the welfare fairness objective function restricts its application to small-scale networks with only a few hundred nodes. In this paper, we adopt the objective function of welfare fairness to maximize the exponentially weighted summation over the influenced fraction of all communities. We first introduce an unbiased estimator for the fractional power of the arithmetic mean. Then, by adapting the reverse influence sampling (RIS) approach, we convert the optimization problem to a weighted maximum coverage problem. We also analyze the number of reverse reachable sets needed to approximate the fair influence at a high probability. Further, we present an efficient algorithm that guarantees \(1-1/e - \varepsilon\) approximation.

SPOTLIGHT-1: Curriculum Learning With Infant Egocentric Videos

Keywords: Curriculum learning Self-supervised learning Slow changes Infant development

Scores: [ 7 7 6 6 ]

Infants possess a remarkable ability to rapidly learn and process visual inputs. As an infant's mobility increases, so does the variety and dynamics of their visual inputs. Is this change in the properties of the visual inputs beneficial or even critical for the proper development of the visual system? To address this question, we used video recordings from infants wearing head-mounted cameras to train a variety of self-supervised learning models. Critically, we separated the infant data by age group and evaluated the importance of training with a curriculum aligned with developmental order. We found that initiating learning with the data from the youngest age group provided the strongest learning signal and led to the best learning outcomes in terms of downstream task performance. We then showed that the benefits of the data from the youngest age group are due to the slowness and simplicity of the visual experience. The results provide strong empirical evidence for the importance of the properties of the early infant experience and developmental progression in training. More broadly, our approach and findings take a noteworthy step towards reverse engineering the learning mechanisms in newborn brains using image-computable models from artificial intelligence.

POSTER-18: Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions

Keywords: individual fairness; similarity learning; active learning

Scores: [ 4 7 8 2 ]

Similarity functions measure how comparable pairs of elements are, and play a key role in a wide variety of applications, e.g., notions of Individual Fairness abiding by the seminal paradigm of Dwork et al., as well as Clustering problems. However, access to an accurate similarity function should not always be considered guaranteed, and this point was even raised by Dwork et al. For instance, it is reasonable to assume that when the elements to be compared are produced by different distributions, or in other words belong to different ``demographic'' groups, knowledge of their true similarity might be very difficult to obtain. In this work, we present an efficient sampling framework that learns these across-groups similarity functions, using only a limited amount of experts' feedback. We show analytical results with rigorous theoretical bounds, and empirically validate our algorithms via a large suite of experiments.

POSTER-19: Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventions

Keywords: Machine learning for healthcare Causal mediation Gaussian process Point Process

Scores: [ 7 5 5 7 ]

Deciding on an appropriate intervention requires a causal model of a treatment, the outcome, and potential mediators. Causal mediation analysis lets us distinguish between direct and indirect effects of the intervention, but has mostly been studied in a static setting. In healthcare, data come in the form of complex, irregularly sampled time-series, with dynamic interdependencies between a treatment, outcomes, and mediators across time. Existing approaches to dynamic causal mediation analysis are limited to regular measurement intervals, simple parametric models, and disregard long-range mediator--outcome interactions. To address these limitations, we propose a non-parametric mediator--outcome model where the mediator is assumed to be a temporal point process that interacts with the outcome process. With this model, we estimate the direct and indirect effects of an external intervention on the outcome, showing how each of these affects the whole future trajectory. We demonstrate on semi-synthetic data that our method can accurately estimate direct and indirect effects. On real-world healthcare data, our model infers clinically meaningful direct and indirect effect trajectories for blood glucose after a surgery.

POSTER-20: Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction

Keywords: unsupervised anomaly detection global explanation rule extraction

Scores: [ 5 5 6 5 ]

Many security applications require unsupervised anomaly detection, as malicious data are extremely rare and often only unlabeled normal data are available for training (i.e., zero-positive). However, security operators are concerned about the high stakes of trusting black-box models due to their lack of interpretability. In this paper, we propose a post-hoc method to globally explain a black-box unsupervised anomaly detection model via rule extraction.First, we propose the concept of distribution decomposition rules that decompose the complex distribution of normal data into multiple compositional distributions. To find such rules, we design an unsupervised Interior Clustering Tree that incorporates the model prediction into the splitting criteria. Then, we propose the Compositional Boundary Exploration (CBE) algorithm to obtain the boundary inference rules that estimate the decision boundary of the original model on each compositional distribution. By merging these two types of rules into a rule set, we can present the inferential process of the unsupervised black-box model in a human-understandable way, and build a surrogate rule-based model for online deployment at the same time. We conduct comprehensive experiments on the explanation of four distinct unsupervised anomaly detection models on various real-world datasets. The evaluation shows that our method outperforms existing methods in terms of diverse metrics including fidelity, correctness and robustness.

POSTER-21: Counting Distinct Elements Under Person-Level Differential Privacy

Keywords: differential privacy user-level privacy person-level privacy sensitivity

Scores: [ 7 6 5 5 ]

We study the problem of counting the number of distinct elements in a dataset subject to the constraint of differential privacy. We consider the challenging setting of person-level DP (a.k.a. user-level DP) where each person may contribute an unbounded number of items and hence the sensitivity is unbounded.Our approach is to compute a bounded-sensitivity version of this query, which reduces to solving a max-flow problem. The sensitivity bound is optimized to balance the noise we must add to privatize the answer against the error of the approximation of the bounded-sensitivity query to the true number of unique elements.

SPOTLIGHT-2: Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

Keywords: Theory of reinforcement learning policy optimization

Scores: [ 8 7 7 7 7 ]

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited---they are either restricted to tabular MDPs or suffer from highly suboptimal sample complexity, especial in online RL where exploration is necessary. This paper proposes a simple efficient policy optimization framework---Optimistic NPG for online RL. Optimistic NPG can be viewed as simply combining of the classic natural policy gradient (NPG) algorithm [Kakade, 2001] with optimistic policy evaluation subroutines to encourage exploration. For \(d\)-dimensional linear MDPs, Optimistic NPG is computationally efficient, and learns an \(\epsilon\)-optimal policy within \(\tilde{\mathcal{O}}(d^2/\epsilon^3)\) samples, which is the first computationally efficient algorithm whose sample complexity has the optimal dimension dependence \(\tilde{\Theta}(d^2)\). It also improves over state-of-the-art results of policy optimization algorithms [Zanette et al., 2021] by a factor of \(d\). For general function approximation that subsumes linear MDPs, Optimistic NPG, to our best knowledge, is also the first policy optimization algorithm that achieves the polynomial sample complexity for learning near-optimal policies.

POSTER-22: Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference

Keywords: Adaptive linear regression bandit algorithms high dimensional statistics statistical inference

Scores: [ 5 6 7 5 7 5 ]

Estimation and inference in statistics pose significant challenges when data are collected adaptively. Even in linear models, the Ordinary Least Squares (OLS) estimator may fail to exhibit asymptotic normality for single coordinate estimation and have inflated error. This issue is highlighted by a recent minimax lower bound, which shows that the error of estimating a single coordinate can be enlarged by a multiple of \(\sqrt{d}\) when data are allowed to be arbitrarily adaptive, compared with the case when they are i.i.d. Our work explores this striking difference in estimation performance between utilizing i.i.d. and adaptive data. We investigate how the degree of adaptivity in data collection impacts the performance of estimating a low-dimensional parameter component in high-dimensional linear models. We identify conditions on the data collection mechanism under which the estimation error for a low-dimensional parameter component matches its counterpart in the i.i.d. setting, up to a factor that depends on the degree of adaptivity. We show that OLS or OLS on centered data can achieve this matching error. In addition, we propose a novel estimator for single coordinate inference via solving a Two-stage Adaptive Linear Estimating equation (TALE). Under a weaker form of adaptivity in data collection, we establish an asymptotic normality property of the proposed estimator.

POSTER-23: Universality and Limitations of Prompt Tuning

Keywords: prompt-tuning; language model; expressive power

Scores: [ 6 5 5 6 7 ]

Despite the demonstrated empirical efficacy of prompt tuning to adapt a pretrained language model for a new task, the theoretical underpinnings of the difference between "tuning parameters before the input" against "the tuning of model weights" are limited. We thus take one of the first steps to understand the role of soft-prompt tuning for transformer-based architectures. By considering a general purpose architecture, we analyze prompt tuning from the lens of both: universal approximation and limitations with finite-depth fixed-weight pretrained transformers for continuous-valued functions. Our universality result guarantees the existence of a strong transformer with a prompt to approximate any sequence-to-sequence function in the set of Lipschitz functions. The limitations of prompt tuning for limited-depth transformers are first proved by constructing a set of datasets, that cannot be memorized by a prompt of any length for a given single encoder layer. We also provide a lower bound on the required number of tunable prompt parameters and compare the result with the number of parameters required for a low-rank update (based on LoRA) for a single-layer setting. We finally extend our analysis to multi-layer settings by providing sufficient conditions under which the transformer can at best learn datasets from invertible functions only. Our theoretical claims are also corroborated by empirical results.

SPOTLIGHT-3: Unpaired Multi-Domain Causal Representation Learning

Keywords: linear structural equation models causality representation learning independent component analysis structure identifiability multiple views graphical model

Scores: [ 7 6 7 6 ]

POSTER-24: \(S^3\): Increasing GPU Utilization during Generative Inference for Higher Throughput

Keywords: Throughput GPU utilization Sequence length prediction

Scores: [ 5 6 7 5 6 ]

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even larger than the model itself. This problem is exacerbated in one of the current LLM serving frameworks which reserves the maximum sequence length of memory for the KV cache to guarantee generating a complete sequence as they do not know the output sequence length. This restricts us to use a smaller batch size leading to lower GPU utilization and above all, lower throughput. We argue that designing a system with a priori knowledge of the output sequence can mitigate this problem. To this end, we propose \(S^3\), which predicts the output sequence length, schedules generation queries based on the prediction to increase device resource utilization and throughput, and handle mispredictions. Our proposed method achieves 6.49× throughput over those systems that assume the worst case for the output sequence length.

POSTER-25: Beta Diffusion

Keywords: Diffusion models KL-divergence upper bounds multiplicative transitions scaled and shifted beta distributions

Scores: [ 6 7 6 6 ]

We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges. Using scaled and shifted beta distributions, beta diffusion utilizes multiplicative transitions over time to create both forward and reverse diffusion processes, maintaining beta distributions in both the forward marginals and the reverse conditionals, given the data at any point in time. Unlike traditional diffusion-based generative models relying on additive Gaussian noise and reweighted evidence lower bounds (ELBOs), beta diffusion is multiplicative and optimized with KL-divergence upper bounds (KLUBs) derived from the convexity of the KL divergence. We demonstrate that the proposed KLUBs are more effective for optimizing beta diffusion compared to negative ELBOs, which can also be derived as the KLUBs of the same KL divergence with its two arguments swapped. The loss function of beta diffusion, expressed in terms of Bregman divergence, further supports the efficacy of KLUBs for optimization. Experimental results on both synthetic data and natural images demonstrate the unique capabilities of beta diffusion in generative modeling of range-bounded data and validate the effectiveness of KLUBs in optimizing diffusion models, thereby making them valuable additions to the family of diffusion-based generative models and the optimization techniques used to train them.

SPOTLIGHT-4: Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio

Keywords: sound field spatial audio virtual humans human body body modeling

Scores: [ 7 7 8 5 ]

While 3D human body modeling has received much attention in computer vision, modeling the acoustic equivalent, i.e. modeling 3D spatial audio produced by body motion and speech, has fallen short in the community. To close this gap, we present a model that can generate accurate 3D spatial audio for full human bodies. The system consumes, as input, audio signals from headset microphones and body pose, and produces, as output, a 3D sound field surrounding the transmitter's body, from which spatial audio can be rendered at any arbitrary position in the 3D space. We collect a first-of-its-kind multimodal dataset of human bodies, recorded with multiple cameras and a spherical array of 345 microphones. In an empirical evaluation, we demonstrate that our model can produce accurate body-induced sound fields when trained with a suitable loss. Dataset and code are available online.

POSTER-26: Optimized Covariance Design for AB Test on Social Network under Interference

Keywords: AB test interference causal inference optimization social network

Scores: [ 6 6 7 5 ]

POSTER-27: Multi-scale Diffusion Denoised Smoothing

Keywords: adversarial robustness certified robustness randomized smoothing denoised smoothing diffusion models

Scores: [ 5 6 6 5 5 ]

Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre-trained models. Specifically, one can perform randomized smoothing on any classifier via a simple "denoise-and-classify" pipeline, so-called denoised smoothing, given that an accurate denoiser is available - such as diffusion model. In this paper, we present scalable methods to address the current trade-off between certified robustness and accuracy in denoised smoothing. Our key idea is to "selectively" apply smoothing among multiple noise scales, coined multi-scale smoothing, which can be efficiently implemented with a single diffusion model. This approach also suggests a new objective to compare the collective robustness of multi-scale smoothed classifiers, and questions which representation of diffusion model would maximize the objective. To address this, we propose to further fine-tune diffusion model (a) to perform consistent denoising whenever the original image is recoverable, but (b) to generate rather diverse outputs otherwise. Our experiments show that the proposed multi-scale smoothing scheme, combined with diffusion fine-tuning, not only allows strong certified robustness at high noise scales but also maintains accuracy close to non-smoothed classifiers. Code is available at

POSTER-28: Conformal PID Control for Time Series Prediction

Keywords: conformal prediction time series uncertainty quantification distribution shift

Scores: [ 6 7 6 5 ]

POSTER-29: Residual Alignment: Uncovering the Mechanisms of Residual Networks

Keywords: Deep Learning Residual Networks Neural Networks Generalization Spectral Analysis

Scores: [ 8 7 6 7 ]

The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this paper, we conduct a thorough empirical study of the ResNet architecture in classification tasks by linearizing its constituent residual blocks using Residual Jacobians and measuring their singular value decompositions. Our measurements (code) reveal a process called Residual Alignment (RA) characterized by four properties:- (RA1): intermediate representations of a given input are equispaced on a line, embedded in high dimensional space, as observed by Gai and Zhang [2021];- (RA2): top left and right singular vectors of Residual Jacobians align with each other and across different depths;- (RA3): Residual Jacobians are at most rank \(C\) for fully-connected ResNets, where \(C\) is the number of classes; and- (RA4): top singular values of Residual Jacobians scale inversely with depth.RA consistently occurs in models that generalize well, in both fully-connected and convolutional architectures, across various depths and widths, for varying numbers of classes, on all tested benchmark datasets, but ceases to occur once the skip connections are removed. It also provably occurs in a novel mathematical model we propose. This phenomenon reveals a strong alignment between residual branches of a ResNet (RA2+4), imparting a highly rigid geometric structure to the intermediate representations as they progress linearly through the network (RA1) up to the final layer, where they undergo Neural Collapse.

POSTER-30: Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints

Keywords: neural differential equations neural ordinary differential equations constraints conservation laws stabilization dynamical systems dynamics scientific machine learning physics-informed machine learning

Scores: [ 3 6 6 6 7 ]

Many successful methods to learn dynamical systems from data have recently been introduced. However, ensuring that the inferred dynamics preserve known constraints, such as conservation laws or restrictions on the allowed system states, remains challenging. We propose stabilized neural differential equations (SNDEs), a method to enforce arbitrary manifold constraints for neural differential equations. Our approach is based on a stabilization term that, when added to the original dynamics, renders the constraint manifold provably asymptotically stable. Due to its simplicity, our method is compatible with all common neural differential equation (NDE) models and broadly applicable. In extensive empirical evaluations, we demonstrate that SNDEs outperform existing methods while broadening the types of constraints that can be incorporated into NDE training.

POSTER-31: P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

Keywords: text-to-speech zero-shot TTS flow matching generative model

Scores: [ 5 5 6 6 ]

While recent large-scale neural codec language models have shown significant improvement in zero-shot TTS by training on thousands of hours of data, they suffer from drawbacks such as a lack of robustness, slow sampling speed similar to previous autoregressive TTS methods, and reliance on pre-trained neural codec representations. Our work proposes P-Flow, a fast and data-efficient zero-shot TTS model that uses speech prompts for speaker adaptation. P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis. Our speech-prompted text encoder uses speech prompts and text input to generate speaker-conditional text representation. The flow matching generative decoder uses the speaker-conditional output to synthesize high-quality personalized speech significantly faster than in real-time. Unlike the neural codec language models, we specifically train P-Flow on LibriTTS dataset using a continuous mel-representation. Through our training method using continuous speech prompts, P-Flow matches the speaker similarity performance of the large-scale zero-shot TTS models with two orders of magnitude less training data and has more than 20$\times$ faster sampling speed. Our results show that P-Flow has better pronunciation and is preferred in human likeness and speaker similarity to its recent state-of-the-art counterparts, thus defining P-Flow as an attractive and desirable alternative. We provide audio samples on our demo page:

POSTER-32: FAMO: Fast Adaptive Multitask Optimization

Keywords: multitask learning multitask optimization conflicting gradients knowledge transfer

Scores: [ 7 6 5 6 ]

One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL). However, in practice, applying gradient descent (GD) on the average loss across all tasks may yield poor multitask performance due to severe under-optimization of certain tasks. Previous approaches that manipulate task gradients for a more balanced loss decrease require storing and computing all task gradients (\(\mathcal{O}(k)\) space and time where \(k\) is the number of tasks), limiting their use in large-scale scenarios. In this work, we introduce Fast Adaptive Multitask Optimization (FAMO), a dynamic weighting method that decreases task losses in a balanced way using \(\mathcal{O}(1)\) space and time. We conduct an extensive set of experiments covering multi-task supervised and reinforcement learning problems. Our results indicate that FAMO achieves comparable or superior performance to state-of-the-art gradient manipulation techniques while offering significant improvements in space and computational efficiency. Code is available at \url{}.

POSTER-33: Implicit variance regularization in non-contrastive SSL

Keywords: Self-supervised learning Non-contrastive learning Learning dynamics

Scores: [ 6 7 5 ]

Non-contrastive SSL methods like BYOL and SimSiam rely on asymmetric predictor networks to avoid representational collapse without negative samples. Yet, how predictor networks facilitate stable learning is not fully understood. While previous theoretical analyses assumed Euclidean losses, most practical implementations rely on cosine similarity. To gain further theoretical insight into non-contrastive SSL, we analytically study learning dynamics in conjunction with Euclidean and cosine similarity in the eigenspace of closed-form linear predictor networks. We show that both avoid collapse through implicit variance regularization albeit through different dynamical mechanisms. Moreover, we find that the eigenvalues act as effective learning rate multipliers and propose a family of isotropic loss functions (IsoLoss) that equalize convergence rates across eigenmodes. Empirically, IsoLoss speeds up the initial learning dynamics and increases robustness, thereby allowing us to dispense with the EMA target network typically used with non-contrastive methods. Our analysis sheds light on the variance regularization mechanisms of non-contrastive SSL and lays the theoretical grounds for crafting novel loss functions that shape the learning dynamics of the predictor's spectrum.

POSTER-34: New Complexity-Theoretic Frontiers of Tractability for Neural Network Training

Keywords: neural network training computational complexity ReLU networks Linear networks

Scores: [ 6 7 6 6 5 ]

In spite of the fundamental role of neural networks in contemporary machine learning research, our understanding of the computational complexity of optimally training neural networks remains limited even when dealing with the simplest kinds of activation functions. Indeed, while there has been a number of very recent results that establish ever-tighter lower bounds for the problem under linear and ReLU activation functions, little progress has been made towards the identification of novel polynomial-time tractable network architectures. In this article we obtain novel algorithmic upper bounds for training linear- and ReLU-activated neural networks to optimality which push the boundaries of tractability for these problems beyond the previous state of the art.

POSTER-35: Optimal Treatment Regimes for Proximal Causal Learning

Keywords: Optimal treatment regimes Policy-making Proximal causal inference Unmeasured confounding Value function

Scores: [ 5 7 6 6 ]

A common concern when a policymaker draws causal inferences from and makes decisions based on observational data is that the measured covariates are insufficiently rich to account for all sources of confounding, i.e., the standard no confoundedness assumption fails to hold. The recently proposed proximal causal inference framework shows that proxy variables that abound in real-life scenarios can be leveraged to identify causal effects and therefore facilitate decision-making. Building upon this line of work, we propose a novel optimal individualized treatment regime based on so-called outcome and treatment confounding bridges. We then show that the value function of this new optimal treatment regime is superior to that of existing ones in the literature. Theoretical guarantees, including identification, superiority, excess value bound, and consistency of the estimated regime, are established. Furthermore, we demonstrate the proposed optimal regime via numerical experiments and a real data application.

POSTER-36: Multi-Swap k-Means++

Keywords: Clustering k-means approximation algorithms

Scores: [ 8 3 7 7 ]

POSTER-37: Automated Classification of Model Errors on ImageNet

Keywords: ImageNet evaluation error classification error analysis

Scores: [ 6 7 5 5 4 ]

While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and evaluation protocols have been proposed for ImageNet showing that state-of-the-art models already achieve over 95% accuracy and shifting the focus on investigating why the remaining errors persist.Recent work in this direction employed a panel of experts to manually categorize all remaining classification errors for two selected models. However, this process is time-consuming, prone to inconsistencies, and requires trained experts, making it unsuitable for regular model evaluation thus limiting its utility. To overcome these limitations, we propose the first automated error classification framework, a valuable tool to study how modeling choices affect error distributions. We use our framework to comprehensively evaluate the error distribution of over 900 models. Perhaps surprisingly, we find that across model architectures, scales, and pre-training corpora, top-1 accuracy is a strong predictor for the portion of all error types. In particular, we observe that the portion of severe errors drops significantly with top-1 accuracy indicating that, while it underreports a model's true performance, it remains a valuable performance metric.We release all our code at

POSTER-38: (Amplified) Banded Matrix Factorization: A unified approach to private training

Keywords: Machine Learning Differential Privacy Optimization Private Machine Learning Federated Learning Privacy Amplification Matrix Factorization

Scores: [ 6 5 5 8 6 ]

Matrix factorization (MF) mechanisms for differential privacy (DP) have substantially improved the state-of-the-art in privacy-utility-computation tradeoffs for ML applications in a variety of scenarios, but in both the centralized and federated settings there remain instances where either MF cannot be easily applied, or other algorithms provide better tradeoffs (typically, as \(\epsilon\) becomes small).In this work, we show how MF can subsume prior state-of-the-art algorithms in both federated and centralized training settings, across all privacy budgets. The key technique throughout is the construction of MF mechanisms with banded matrices (lower-triangular matrices with at most \(\hat{b}\) nonzero bands including the main diagonal). For cross-device federated learning (FL), this enables multiple-participations with a relaxed device participation schema compatible with practical FL infrastructure (as demonstrated by a production deployment). In the centralized setting, we prove that banded matrices enjoy the same privacy amplification results as the ubiquitous DP-SGD algorithm, but can provide strictly better performance in most scenarios---this lets us always at least match DP-SGD, and often outperform it

POSTER-39: Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

Keywords: LLMs Planning Domain Model LLMs for Planning LLMs for Heuristic Guidance

Scores: [ 5 6 7 7 ]

There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, strong reliance on feedback from interactions with simulators or even the actual environment, and the inefficiency in utilizing human feedback. In this work, we introduce a novel alternative paradigm that constructs an explicit world (domain) model in planning domain definition language (PDDL) and then uses it to plan with sound domain-independent planners. To address the fact that LLMs may not generate a fully functional PDDL model initially, we employ LLMs as an interface between PDDL and sources of corrective feedback, such as PDDL validators and humans. For users who lack a background in PDDL, we show that LLMs can translate PDDL into natural language and effectively encode corrective feedback back to the underlying domain model. Our framework not only enjoys the correctness guarantee offered by the external planners but also reduces human involvement by allowing users to correct domain models at the beginning, rather than inspecting and correcting (through interactive prompting) every generated plan as in previous work. On two IPC domains and a Household domain that is more complicated than commonly used benchmarks such as ALFWorld, we demonstrate that GPT-4 can be leveraged to produce high-quality PDDL models for over 40 actions, and the corrected PDDL models are then used to successfully solve 48 challenging planning tasks. Resources, including the source code, are released at:

POSTER-40: A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence

Keywords: Theory for Reinforcement Learning Policy Optimization Policy Gradient Mirror Descent.

Scores: [ 6 7 7 5 7 ]

Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe their success to the use of parameterized policies. However, while theoretical guarantees have been established for this class of algorithms, especially in the tabular setting, the use of general parameterization schemes remains mostly unjustified. In this work, we introduce a novel framework for policy optimization based on mirror descent that naturally accommodates general parameterizations. The policy class induced by our scheme recovers known classes, e.g., softmax, and generates new ones depending on the choice of mirror map. Using our framework, we obtain the first result that guarantees linear convergence for a policy-gradient-based method involving general parameterization. To demonstrate the ability of our framework to accommodate general parameterization schemes, we provide its sample complexity when using shallow neural networks, show that it represents an improvement upon the previous best results, and empirically validate the effectiveness of our theoretical claims on classic control tasks.

SPOTLIGHT-5: Quasi-Monte Carlo Graph Random Features

Keywords: Graph discrete mathematics quasi-Monte Carlo kernel scalability Laplacian clustering random walks

Scores: [ 7 7 5 9 ]

We present a novel mechanism to improve the accuracy of the recently-introduced class of graph random features (GRFs). Our method induces negative correlations between the lengths of the algorithm's random walks by imposing antithetic termination: a procedure to sample more diverse random walks which may be of independent interest. It has a trivial drop-in implementation. We derive strong theoretical guarantees on the properties of these quasi-Monte Carlo GRFs (q-GRFs), proving that they yield lower-variance estimators of the \(2\)-regularised Laplacian kernel under mild conditions. Remarkably, our results hold for any graph topology. We demonstrate empirical accuracy improvements on a variety of tasks including a new practical application: time-efficient approximation of the graph diffusion process. To our knowledge, q-GRFs constitute the first rigorously studied quasi-Monte Carlo scheme for kernels defined on combinatorial objects, inviting new research on correlations between graph random walks.

POSTER-41: One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models

Keywords: Generative Models Normalizing Flows Variational Autoencoders

Scores: [ 6 4 6 3 ]

POSTER-42: Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models

Keywords: reinforcement learning generative models offline RL sequential decision making

Scores: [ 3 4 7 6 5 ]

Reinforcement learning presents an attractive paradigm to reason about several distinct aspects of sequential decision making, such as specifying complex goals, planning future observations and actions, and critiquing their utilities. However, the combined integration of these capabilities poses competing algorithmic challenges in retaining maximal expressivity while allowing for flexibility in modeling choices for efficient learning and inference. We present Decision Stacks, a generative framework that decomposes goal-conditioned policy agents into 3 generative modules. These modules simulate the temporal evolution of observations, rewards, and actions via independent generative models that can be learned in parallel via teacher forcing. Our framework guarantees both expressivity and flexibility in designing individual modules to account for key factors such as architectural bias, optimization objective and dynamics, transferrability across domains, and inference speed. Our empirical results demonstrate the effectiveness of Decision Stacks for offline policy optimization for several MDP and POMDP environments, outperforming existing methods and enabling flexible generative decision making.

POSTER-43: Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

Keywords: scientific machine learning scaling transfer learning neural operators foundation models

Scores: [ 7 6 6 6 ]

Pre-trained machine learning (ML) models have shown great performance for awide range of applications, in particular in natural language processing (NLP)and computer vision (CV). Here, we study how pre-training could be used forscientific machine learning (SciML) applications, specifically in the context oftransfer learning. We study the transfer behavior of these models as (i) the pretrainedmodel size is scaled, (ii) the downstream training dataset size is scaled,(iii) the physics parameters are systematically pushed out of distribution, and (iv)how a single model pre-trained on a mixture of different physics problems canbe adapted to various downstream applications. We find that—when fine-tunedappropriately—transfer learning can help reach desired accuracy levels with ordersof magnitude fewer downstream examples (across different tasks that can even beout-of-distribution) than training from scratch, with consistent behaviour across awide range of downstream examples. We also find that fine-tuning these modelsyields more performance gains as model size increases, compared to training fromscratch on new downstream tasks. These results hold for a broad range of PDElearning tasks. All in all, our results demonstrate the potential of the “pre-train andfine-tune” paradigm for SciML problems, demonstrating a path towards buildingSciML foundation models. Our code is available as open-source.

POSTER-44: CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Keywords: Image to image translation latent diffusion models conditional diffusion models

Scores: [ 6 2 6 5 5 ]

Diffusion models (DMs) have enabled breakthroughs in image synthesis tasks but lack an intuitive interface for consistent image-to-image (I2I) translation. Various methods have been explored to address this issue, including mask-based methods, attention-based methods, and image-conditioning. However, it remains a critical challenge to enable unpaired I2I translation with pre-trained DMs while maintaining satisfying consistency. This paper introduces Cyclenet, a novel but simple method that incorporates cycle consistency into DMs to regularize image manipulation. We validate Cyclenet on unpaired I2I tasks of different granularities. Besides the scene and object level translation, we additionally contribute a multi-domain I2I translation dataset to study the physical state changes of objects. Our empirical studies show that Cyclenet is superior in translation consistency and quality, and can generate high-quality images for out-of-domain distributions with a simple change of the textual prompt. Cyclenet is a practical framework, which is robust even with very limited training data (around 2k) and requires minimal computational resources (1 GPU) to train. Project homepage:

POSTER-45: A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

Keywords: Generative adversarial network inverse problems posterior sampling cGAN GAN

Scores: [ 6 7 6 5 ]

In image recovery problems, one seeks to infer an image from distorted, incomplete, and/or noise-corrupted measurements.Such problems arise in magnetic resonance imaging (MRI), computed tomography, deblurring, super-resolution, inpainting, phase retrieval, image-to-image translation, and other applications. Given a training set of signal/measurement pairs, we seek to do more than just produce one good image estimate. Rather, we aim to rapidly and accurately sample from the posterior distribution. To do this,we propose a regularized conditional Wasserstein GAN that generates dozens of high-quality posterior samples per second. Our regularization comprises an \(\ell_1\) penalty and an adaptively weighted standard-deviation reward. Using quantitative evaluation metrics like conditional Fréchet inception distance, we demonstrate that our method produces state-of-the-art posterior samples in both multicoil MRI and large-scale inpainting applications. The code for our model can be found here:

POSTER-46: Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization

Keywords: deep learning graph neural network out-of-distribution generalization distribution shift

Scores: [ 5 3 5 6 6 ]

We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs. We further develop an adversarial training strategy to jointly optimize these two properties for casual subgraph discovery with theoretical guarantees. Extensive experiments and analysis show that LECI significantly outperforms prior methods on both synthetic and real-world datasets, establishing LECI as a practical and effective solution for graph OOD generalization.

SPOTLIGHT-6: Online List Labeling with Predictions

Keywords: Algorithms with Predictions Data Structures Learned Indices Online List Labeling Resource Allocation Beyond Worst Case Analysis

Scores: [ 8 8 7 6 ]

A growing line of work shows how learned predictions can be used to break through worst-case barriers to improve the running time of an algorithm. However, incorporating predictions into data structures with strong theoretical guarantees remains underdeveloped. This paper takes a step in this direction by showing that predictions can be leveraged in the fundamental online list labeling problem. In the problem, \(n\) items arrive over time and must be stored in sorted order in an array of size \(\Theta(n)\). The array slot of an element is its label and the goal is to maintain sorted order while minimizing the total number of elements moved (i.e., relabeled). We design a new list labeling data structure and bound its performance in two models. In the worst-case learning-augmented model, we give guarantees in terms of the error in the predictions. Our data structure provides strong guarantees: it is optimal for any prediction error and guarantees the best-known worst-case bound even when the predictions are entirely erroneous. We also consider a stochastic error model and bound the performance in terms of the expectation and variance of the error. Finally, the theoretical results are demonstrated empirically. In particular, we show that our data structure has strong performance on real temporal data sets where predictions are constructed from elements that arrived in the past, as is typically done in a practical use case.

POSTER-47: Thin and deep Gaussian processes

Keywords: Gaussian Processes Deep Gaussian Processes non-stationary kernels

Scores: [ 7 4 4 7 ]

Gaussian processes (GPs) can provide a principled approach to uncertainty quantification with easy-to-interpret kernel hyperparameters, such as the lengthscale, which controls the correlation distance of function values.However, selecting an appropriate kernel can be challenging.Deep GPs avoid manual kernel engineering by successively parameterizing kernels with GP layers, allowing them to learn low-dimensional embeddings of the inputs that explain the output data.Following the architecture of deep neural networks, the most common deep GPs warp the input space layer-by-layer but lose all the interpretability of shallow GPs. An alternative construction is to successively parameterize the lengthscale of a kernel, improving the interpretability but ultimately giving away the notion of learning lower-dimensional embeddings. Unfortunately, both methods are susceptible to particular pathologies which may hinder fitting and limit their interpretability.This work proposes a novel synthesis of both previous approaches: {Thin and Deep GP} (TDGP). Each TDGP layer defines locally linear transformations of the original input data maintaining the concept of latent embeddings while also retaining the interpretation of lengthscales of a kernel. Moreover, unlike the prior solutions, TDGP induces non-pathological manifolds that admit learning lower-dimensional representations.We show with theoretical and experimental results that i) TDGP is, unlike previous models, tailored to specifically discover lower-dimensional manifolds in the input data, ii) TDGP behaves well when increasing the number of layers, and iii) TDGP performs well in standard benchmark datasets.

SPOTLIGHT-7: Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers

Keywords: Transformer Normalization Layer Normalization RMSNorm Efficient Machine Learning

Scores: [ 7 5 7 7 ]

Transformers have achieved great success in machine learning applications.Normalization techniques, such as Layer Normalization (LayerNorm, LN) and Root Mean Square Normalization (RMSNorm), play a critical role in accelerating and stabilizing the training of Transformers.While LayerNorm recenters and rescales input vectors, RMSNorm only rescales the vectors by their RMS value.Despite being more computationally efficient, RMSNorm may compromise the representation ability of Transformers.There is currently no consensus regarding the preferred normalization technique, as some models employ LayerNorm while others utilize RMSNorm, especially in recent large language models.It is challenging to convert Transformers with one normalization to the other type.While there is an ongoing disagreement between the two normalization types,we propose a solution to unify two mainstream Transformer architectures, Pre-LN and Pre-RMSNorm Transformers.By removing the inherent redundant mean information in the main branch of Pre-LN Transformers, we can reduce LayerNorm to RMSNorm, achieving higher efficiency.We further propose the Compressed RMSNorm (CRMSNorm) and Pre-CRMSNorm Transformer based on a lossless compression of the zero-mean vectors.We formally establish the equivalence of Pre-LN, Pre-RMSNorm, and Pre-CRMSNorm Transformer variants in both training and inference.It implies that Pre-LN Transformers can be substituted with Pre-(C)RMSNorm counterparts at almost no cost, offering the same arithmetic functionality along with free efficiency improvement.Experiments demonstrate that we can reduce the training and inference time of Pre-LN Transformers by 1% - 10%.

POSTER-48: SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks

Keywords: spiking networks event-based simulation sparse networks backpropagation algorithm neuroscience

Scores: [ 9 7 4 4 ]

Spiking Neural Networks (SNNs) are biologically-inspired models that are capable of processing information in streams of action potentials. However, simulating and training SNNs is computationally expensive due to the need to solve large systems of coupled differential equations. In this paper, we propose a novel event-based algorithm called SparseProp for simulating and training sparse SNNs. Our algorithm reduces the computational cost of both forward pass and backward pass operations from O(N) to O(log(N)) per network spike, enabling numerically exact simulations of large spiking networks and their efficient training using backpropagation through time. By exploiting the sparsity of the network, SparseProp avoids iterating through all neurons at every spike and uses efficient state updates. We demonstrate the effectiveness of SparseProp for several classical integrate-and-fire neuron models, including simulating a sparse SNN with one million LIF neurons, which is sped up by more than four orders of magnitude compared to previous implementations. Our work provides an efficient and exact solution for training large-scale spiking neural networks and opens up new possibilities for building more sophisticated brain-inspired models.

POSTER-49: What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

Keywords: poisoning attacks; adversarial machine learning; machine learning security

Scores: [ 5 6 7 6 ]

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear learners on some datasets are able to resist the best known attacks even without any defenses, we further investigate whether datasets can be inherently robust to indiscriminate poisoning attacks for linear learners. For theoretical Gaussian distributions, we rigorously characterize the behavior of an optimal poisoning attack, defined as the poisoning strategy that attains the maximum risk of the induced model at a given poisoning budget. Our results prove that linear learners can indeed be robust to indiscriminate poisoning if the class-wise data distributions are well-separated with low variance and the size of the constraint set containing all permissible poisoning points is also small. These findings largely explain the drastic variation in empirical attack performance of the state-of-the-art poisoning attacks on linear learners across benchmark datasets, making an important initial step towards understanding the underlying reasons some learning tasks are vulnerable to data poisoning attacks.

POSTER-50: Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness

Keywords: Deep Learning Knowledge Distillation Adversarial Training Fairness

Scores: [ 6 5 7 6 7 ]

Adversarial Robustness Distillation (ARD) aims to transfer the robustness of large teacher models to small student models, facilitating the attainment of robust performance on resource-limited devices. However, existing research on ARD primarily focuses on the overall robustness of student models, overlooking the crucial aspect of \(\textit{robust fairness}\). Specifically, these models may demonstrate strong robustness on some classes of data while exhibiting high vulnerability on other classes. Unfortunately, the "buckets effect" implies that the robustness of the deployed model depends on the classes with the lowest level of robustness. In this paper, we first investigate the inheritance of robust fairness during ARD and reveal that student models only partially inherit robust fairness from teacher models. We further validate this issue through fine-grained experiments with various model capacities and find that it may arise due to the gap in capacity between teacher and student models, as well as the existing methods treating each class equally during distillation. Based on these observations, we propose \(\textbf{Fair}\) $\textbf{A}$dversarial $\textbf{R}$obustness $\textbf{D}$istillation (Fair-ARD), a novel framework for enhancing the robust fairness of student models by increasing the weights of difficult classes, and design a geometric perspective-based method to quantify the difficulty of different classes for determining the weights. Extensive experiments show that Fair-ARD surpasses both state-of-the-art ARD methods and existing robust fairness algorithms in terms of robust fairness (e.g., the worst-class robustness under AutoAttack is improved by at most 12.3% and 5.3% using ResNet18 on CIFAR10, respectively), while also slightly improving overall robustness. Our code is available at:

POSTER-51: Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

Keywords: extensive-form games deep reinforcement learning mechanism design correlated equilibria

Scores: [ 7 6 5 6 ]

We introduce a new approach for computing optimal equilibria via learning in games. It applies to extensive-form settings with any number of players, including mechanism design, information design, and solution concepts such as correlated, communication, and certification equilibria. We observe that optimal equilibria are minimax equilibrium strategies of a player in an extensive-form zero-sum game. This reformulation allows to apply techniques for learning in zero-sum games, yielding the first learning dynamics that converge to optimal equilibria, not only in empirical averages, but also in iterates. We demonstrate the practical scalability and flexibility of our approach by attaining state-of-the-art performance in benchmark tabular games, and by computing an optimal mechanism for a sequential auction design problem using deep reinforcement learning.

SPOTLIGHT-8: Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis

Keywords: Reinforcement learning Long-term credit assignment contribution analysis hindsight credit assignment policy gradient methods

Scores: [ 7 6 6 4 8 6 7 ]

To make reinforcement learning more sample efficient, we need better credit assignment methods that measure an action’s influence on future rewards. Building upon Hindsight Credit Assignment (HCA), we introduce Counterfactual Contribution Analysis (COCOA), a new family of model-based credit assignment algorithms. Our algorithms achieve precise credit assignment by measuring the contribution of actions upon obtaining subsequent rewards, by quantifying a counterfactual query: ‘Would the agent still have reached this reward if it had taken another action?’. We show that measuring contributions w.r.t. rewarding states, as is done in HCA, results in spurious estimates of contributions, causing HCA to degrade towards the high-variance REINFORCE estimator in many relevant environments. Instead, we measure contributions w.r.t. rewards or learned representations of the rewarding objects, resulting in gradient estimates with lower variance. We run experiments on a suite of problems specifically designed to evaluate long-term credit assignment capabilities. By using dynamic programming, we measure ground-truth policy gradients and show that the improved performance of our new model-based credit assignment methods is due to lower bias and variance compared to HCA and common baselines. Our results demonstrate how modeling action contributions towards rewarding outcomes can be leveraged for credit assignment, opening a new path towards sample-efficient reinforcement learning.

POSTER-52: Canonical normalizing flows for manifold learning

Keywords: manifold learning flows normalizing flows optimization orthogonalization sparsity sparse learning generative modeling Riemannian manifold geometry metric tensor orthogonal basis

Scores: [ 6 5 7 5 ]

Manifold learning flows are a class of generative modelling techniques that assume a low-dimensional manifold description of the data. The embedding of such a manifold into the high-dimensional space of the data is achieved via learnable invertible transformations. Therefore, once the manifold is properly aligned via a reconstruction loss, the probability density is tractable on the manifold and maximum likelihood can be used to optimize the network parameters. Naturally, the lower-dimensional representation of the data requires an injective-mapping. Recent approaches were able to enforce that the density aligns with the modelled manifold, while efficiently calculating the density volume-change term when embedding to the higher-dimensional space. However, unless the injective-mapping is analytically predefined, the learned manifold is not necessarily an \emph{efficient representation} of the data. Namely, the latent dimensions of such models frequently learn an entangled intrinsic basis, with degenerate information being stored in each dimension. Alternatively, if a locally orthogonal and/or sparse basis is to be learned, here coined canonical intrinsic basis, it can serve in learning a more compact latent space representation. Toward this end, we propose a canonical manifold learning flow method, where a novel optimization objective enforces the transformation matrix to have few prominent and non-degenerate basis functions. We demonstrate that by minimizing the off-diagonal manifold metric elements \(\ell_1\)-norm, we can achieve such a basis, which is simultaneously sparse and/or orthogonal. Canonical manifold flow yields a more efficient use of the latent space, automatically generating fewer prominent and distinct dimensions to represent data, and consequently a better approximation of target distributions than other manifold flow methods in most experiments we conducted, resulting in lower FID scores.

POSTER-53: Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

Keywords: Epidemic Decentralized Learning Randomized Communication Peer sampling

Scores: [ 7 5 6 5 5 ]

We present Epidemic Learning (EL), a simple yet powerful decentralized learning (DL) algorithm that leverages changing communication topologies to achieve faster model convergence compared to conventional DL approaches. At each round of EL, each node sends its model updates to a random sample of \(s\) other nodes (in a system of \(n\) nodes). We provide an extensive theoretical analysis of EL, demonstrating that its changing topology culminates in superior convergence properties compared to the state-of-the-art (static and dynamic) topologies. Considering smooth non-convex loss functions, the number of transient iterations for EL, i.e., the rounds required to achieve asymptotic linear speedup, is in \(O(n^3/s^2)\) which outperforms the best-known bound \(O(n^3)\) by a factor of \(s^2\), indicating the benefit of randomized communication for DL. We empirically evaluate EL in a 96-node network and compare its performance with state-of-the-art DL approaches. Our results illustrate that EL converges up to $ 1.7\times$ quicker than baseline DL algorithms and attains $2.2 $% higher accuracy for the same communication volume.

POSTER-54: Expressivity-Preserving GNN Simulation

Keywords: Graph Neural Networks GNNs Graphs Message Passing Expressiveness Graph Transformations Message Passing Graph Neural Networks

Scores: [ 4 8 7 7 6 6 ]

We systematically investigate graph transformations that enable standard message passing to simulate state-of-the-art graph neural networks (GNNs) without loss of expressivity. Using these, many state-of-the-art GNNs can be implemented with message passing operations from standard libraries, eliminating many sources of implementation issues and allowing for better code optimization. We distinguish between weak and strong simulation: weak simulation achieves the same expressivity only after several message passing steps while strong simulation achieves this after every message passing step. Our contribution leads to a direct way to translate common operations of non-standard GNNs to graph transformations that allow for strong or weak simulation. Our empirical evaluation shows competitive predictive performance of message passing on transformed graphs for various molecular benchmark datasets, in several cases surpassing the original GNNs.

POSTER-55: A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

Keywords: multicalibration multi-objective learning learning theory calibration fairness games

Scores: [ 4 6 6 7 5 ]

We provide a unifying framework for the design and analysis of multi-calibrated predictors. By placing the multi-calibration problem in the general setting of multi-objective learning---where learning guarantees must hold simultaneously over a set of distributions and loss functions---we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multi-calibration learning problems. In addition to shedding light on existing multi-calibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as error tolerances that scale with the square-root of group size versus the constant tolerances guaranteed by prior works, and improving the complexity of \(k\)-class multi-calibration by an exponential factor of \(k\) versus Gopalan et al.. Beyond multi-calibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.

POSTER-56: Emergent Correspondence from Image Diffusion

Keywords: Correspondence Diffusion Model

Scores: [ 7 6 7 7 4 ]

Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images. Without any additional fine-tuning or supervision on the task-specific data or annotations, DIFT is able to outperform both weakly-supervised methods and competitive off-the-shelf features in identifying semantic, geometric, and temporal correspondences. Particularly for semantic correspondence, DIFT from Stable Diffusion is able to outperform DINO and OpenCLIP by 19 and 14 accuracy points respectively on the challenging SPair-71k benchmark. It even outperforms the state-of-the-art supervised methods on 9 out of 18 categories while remaining on par for the overall performance. Project page:

POSTER-57: CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes

Keywords: Embodied AI Interactive Navigation Causal Reinforcement Learning Hierarchical Reinforcement Learning

Scores: [ 7 6 5 7 ]

Visual navigation has been widely studied under the assumption that there may be several clear routes to reach the goal. However, in more practical scenarios such as a house with several messy rooms, there may not. Interactive Navigation (InterNav) considers agents navigating to their goals more effectively with object interactions, posing new challenges of learning interaction dynamics and extra action space. Previous works learn single vision-to-action policy with the guidance of designed representations. However, the causality between actions and outcomes is prone to be confounded when the attributes of obstacles are diverse and hard to measure. Learning policy for long-term action planning in complex scenes also leads to extensive inefficient exploration. In this paper, we introduce a causal diagram of InterNav clarifying the confounding bias caused by obstacles. To address the problem, we propose a multi-policy model that enables the exploration of counterfactual interactions as well as reduces unnecessary exploration. We develop a large-scale dataset containing 600k task episodes in 12k multi-room scenes based on the ProcTHOR simulator and showcase the effectiveness of our method with the evaluations on our dataset.

POSTER-58: TOA: Task-oriented Active VQA

Keywords: knowledge-based visual question answering task-oriented active image understanding large language model visual reasoning multi-round dialogue

Scores: [ 5 7 7 5 ]

Knowledge-based visual question answering (VQA) requires external knowledge to answer the question about an image. Early methods explicitly retrieve knowledge from external knowledge bases, which often introduce noisy information. Recently large language models like GPT-3 have shown encouraging performance as implicit knowledge source and revealed planning abilities. However, current large language models can not effectively understand image inputs, thus it remains an open problem to extract the image information and input to large language models. Prior works have used image captioning and object descriptions to represent the image. However, they may either drop the essential visual information to answer the question correctly or involve irrelevant objects to the task-of-interest. To address this problem, we propose to let large language models make an initial hypothesis according to their knowledge, then actively collect the visual evidence required to verify the hypothesis. In this way, the model can attend to the essential visual information in a task-oriented manner. We leverage several vision modules from the perspectives of spatial attention (i.e., Where to look) and attribute attention (i.e., What to look), which is similar to human cognition. The experiments show that our proposed method outperforms the baselines on open-ended knowledge-based VQA datasets and presents clear reasoning procedure with better interpretability.

POSTER-59: Covariance-adaptive best arm identification

Keywords: Multi-armed bandits Best-arm identification Adaptive identification

Scores: [ 7 6 6 5 5 ]

We consider the problem of best arm identification in the multi-armed bandit model, under fixed confidence. Given a confidence input \(\delta\), the goal is to identify the arm with the highest mean reward with a probability of at least \(1 - \delta\), while minimizing the number of arm pulls. While the literature provides solutions to this problem under the assumption of independent arms distributions, we propose a more flexible scenario where arms can be dependent and rewards can be sampled simultaneously. This framework allows the learner to estimate the covariance among the arms distributions, enabling a more efficient identification of the best arm. The relaxed setting we propose is relevant in various applications, such as clinical trials, where similarities between patients or drugs suggest underlying correlations in the outcomes. We introduce new algorithms that adapt to the unknown covariance of the arms and demonstrate through theoretical guarantees that substantial improvement can be achieved over the standard setting. Additionally, we provide new lower bounds for the relaxed setting and present numerical simulations that support their theoretical findings.

POSTER-60: Model-Based Control with Sparse Neural Dynamics

Keywords: model learning model-based control neural network sparsification mixed-integer programming trajectory optimization

Scores: [ 5 5 6 5 ]

Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current control methods typically rely on extensive sampling or local gradient descent. In this paper, we propose a new framework for integrated model learning and predictive control that is amenable to efficient optimization algorithms. Specifically, we start with a ReLU neural model of the system dynamics and, with minimal losses in prediction accuracy, we gradually sparsify it by removing redundant neurons. This discrete sparsification process is approximated as a continuous problem, enabling an end-to-end optimization of both the model architecture and the weight parameters. The sparsified model is subsequently used by a mixed-integer predictive controller, which represents the neuron activations as binary variables and employs efficient branch-and-bound algorithms. Our framework is applicable to a wide variety of DNNs, from simple multilayer perceptrons to complex graph neural dynamics. It can efficiently handle tasks involving complicated contact dynamics, such as object pushing, compositional object sorting, and manipulation of deformable objects. Numerical and hardware experiments show that, despite the aggressive sparsification, our framework can deliver better closed-loop performance than existing state-of-the-art methods.

POSTER-61: Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

Keywords: federated learning local consistency personalized initialization excess risk

Scores: [ 5 6 6 7 ]

Federated learning (FL) is a distributed paradigm that coordinates massive local clients to collaboratively train a global model via stage-wise local training processes on the heterogeneous dataset. Previous works have implicitly studied that FL suffers from the "client-drift" problem, which is caused by the inconsistent optimum across local clients. However, till now it still lacks solid theoretical analysis to explain the impact of this local inconsistency. To alleviate the negative impact of the "client drift" and explore its substance in FL, in this paper, we first design an efficient FL algorithm FedInit, which allows employing the personalized relaxed initialization state at the beginning of each local training stage. Specifically, FedInit initializes the local state by moving away from the current global state towards the reverse direction of the latest local state. This relaxed initialization helps to revise the local divergence and enhance the local consistency level. Moreover, to further understand how inconsistency disrupts performance in FL, we introduce the excess risk analysis and study the divergence term to investigate the test error of the proposed FedInit method. Our studies show that on the non-convex objectives, optimization error is not sensitive to this local inconsistency, while it mainly affects the generalization error bound in FedInit. Extensive experiments are conducted to validate this conclusion. Our proposed FedInit could achieve state-of-the-art (SOTA) results compared to several advanced benchmarks without any additional costs. Meanwhile, stage-wise relaxed initialization could also be incorporated into the current advanced algorithms to achieve higher performance in the FL paradigm.

POSTER-62: Deep Momentum Multi-Marginal Schrödinger Bridge

Keywords: Schrödinger Bridge Trajectory Inference Optimal Transport

Scores: [ 6 6 6 6 6 ]

It is a crucial challenge to reconstruct population dynamics using unlabeled samples from distributions at coarse time intervals. Recent approaches such as flow-based models or Schrödinger Bridge (SB) models have demonstrated appealing performance, yet the inferred sample trajectories either fail to account for the underlying stochasticity or are unnecessarily rigid. In this article, we extend SB into phase space and propose $\underline{D}$eep $\underline{M}$omentum Multi-Marginal $\underline{S}$chrödinger $\underline{B}$ridge (DMSB), a novel computational framework that learns the smooth measure-valued spline for stochastic systems that satisfy position marginal constraints across time. By tailoring the celebrated Bregman Iteration and extending the Iteration Proportional Fitting to phase space, we manage to handle high-dimensional multi-marginal trajectory inference tasks efficiently. Our algorithm outperforms baselines significantly, as evidenced by experiments for synthetic datasets and a real-world single-cell RNA sequence dataset. Additionally, the proposed approach can reasonably reconstruct the evolution of velocity distribution, from position snapshots only, when there is a ground truth velocity that is nevertheless inaccessible.

POSTER-63: DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model

Keywords: Trajectory Generation Diffusion Model Urban Computing Spatial-temporal Data Mining

Scores: [ 7 7 8 4 ]

Pervasive integration of GPS-enabled devices and data acquisition technologies has led to an exponential increase in GPS trajectory data, fostering advancements in spatial-temporal data mining research. Nonetheless, GPS trajectories contain personal geolocation information, rendering serious privacy concerns when working with raw data. A promising approach to address this issue is trajectory generation, which involves replacing original data with generated, privacy-free alternatives. Despite the potential of trajectory generation, the complex nature of human behavior and its inherent stochastic characteristics pose challenges in generating high-quality trajectories. In this work, we propose a spatial-temporal diffusion probabilistic model for trajectory generation (DiffTraj). This model effectively combines the generative abilities of diffusion models with the spatial-temporal features derived from real trajectories. The core idea is to reconstruct and synthesize geographic trajectories from white noise through a reverse trajectory denoising process. Furthermore, we propose a Trajectory UNet (Traj-UNet) deep neural network to embed conditional information and accurately estimate noise levels during the reverse process. Experiments on two real-world datasets show that DiffTraj can be intuitively applied to generate high-fidelity trajectories while retaining the original distributions. Moreover, the generated results can support downstream trajectory analysis tasks and significantly outperform other methods in terms of geo-distribution evaluations.

POSTER-64: Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

Keywords: benign overfitting kernels neural tangent kernel consistency learning theory

Scores: [ 8 6 6 6 7 ]

The success of over-parameterized neural networks trained to near-zero training error has caused great interest in the phenomenon of benign overfitting, where estimators are statistically consistent even though they interpolate noisy training data. While benign overfitting in fixed dimension has been established for some learning methods, current literature suggests that for regression with typical kernel methods and wide neural networks, benign overfitting requires a high-dimensional setting, where the dimension grows with the sample size. In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough. We generalize existing inconsistency results to non-interpolating models and more kernels to show that benign overfitting with moderate derivatives is impossible in fixed dimension. Conversely, we show that benign overfitting is possible for regression with a sequence of spiky-smooth kernels with large derivatives. Using neural tangent kernels, we translate our results to wide neural networks. We prove that while infinite-width networks do not overfit benignly with the ReLU activation, this can be fixed by adding small high-frequency fluctuations to the activation function. Our experiments verify that such neural networks, while overfitting, can indeed generalize well even on low-dimensional data sets.

POSTER-65: OBJECT 3DIT: Language-guided 3D-aware Image Editing

Keywords: computer vision image editing generative modeling diffusion models 3D

Scores: [ 6 5 5 5 5 ]

Existing image editing tools, while powerful, typically disregard the underlying 3D geometry from which the image is projected. As a result, edits made using these tools may become detached from the geometry and lighting conditions that are at the foundation of the image formation process; such edits break the portrayal of a coherent 3D world. 3D-aware generative models are a promising solution, but currently only succeed on small datasets or at the level of a single object. In this work, we formulate the new task of language-guided 3D-aware editing, where objects in an image should be edited according to a language instruction while remaining consistent with the underlying 3D scene. To promote progress towards this goal, we release OBJect: a benchmark dataset of 400K editing examples created from procedurally generated 3D scenes. Each example consists of an input image, editing instruction in language, and the edited image. We also introduce 3DIT: single and multi-task models for four editing tasks. Our models show impressive abilities to understand the 3D composition of entire scenes, factoring in surrounding objects, surfaces, lighting conditions, shadows, and physically-plausible object configurations. Surprisingly, training on only synthetic scenes from \dataset, editing capabilities of 3DIT generalize to real-world images.

POSTER-66: E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning

Keywords: event camera 2D-3D registration representation learning

Scores: [ 7 5 6 5 ]

Event cameras have emerged as a promising vision sensor in recent years due to their unparalleled temporal resolution and dynamic range. While registration of 2D RGB images to 3D point clouds is a long-standing problem in computer vision, no prior work studies 2D-3D registration for event cameras. To this end, we propose E2PNet, the first learning-based method for event-to-point cloud registration.The core of E2PNet is a novel feature representation network called Event-Points-to-Tensor (EP2T), which encodes event data into a 2D grid-shaped feature tensor. This grid-shaped feature enables matured RGB-based frameworks to be easily used for event-to-point cloud registration, without changing hyper-parameters and the training procedure. EP2T treats the event input as spatio-temporal point clouds. Unlike standard 3D learning architectures that treat all dimensions of point clouds equally, the novel sampling and information aggregation modules in EP2T are designed to handle the inhomogeneity of the spatial and temporal dimensions. Experiments on the MVSEC and VECtor datasets demonstrate the superiority of E2PNet over hand-crafted and other learning-based methods. Compared to RGB-based registration, E2PNet is more robust to extreme illumination or fast motion due to the use of event data. Beyond 2D-3D registration, we also show the potential of EP2T for other vision tasks such as flow estimation, event-to-image reconstruction and object recognition. The source code can be found at:

POSTER-67: Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Keywords: Restless bandits Whittle index policy Q-learning Two-timescale stochastic approximation Neural network function approximation

Scores: [ 7 6 6 7 6 ]

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with \(\mathcal{O}(1/k^{2/3})\) convergence rate, where \(k\) is the number of iterations.

POSTER-68: Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation

Keywords: text-to-image generation; visual programming; text-to-image evaluation; step-by-step generation; interpretability; explainability

Scores: [ 6 7 8 5 6 ]

As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks. While existing work focuses on equipping LMs with visual understanding, we propose two novel interpretable/explainable visual programming frameworks for text-to-image (T2I) generation and evaluation. First, we introduce VPGen, an interpretable step-by-step T2I generation framework that decomposes T2I generation into three steps: object/count generation, layout generation, and image generation. We employ an LM to handle the first two steps (object/count generation and layout generation), by finetuning it on text-layout pairs. Our step-by-step T2I generation framework provides stronger spatial control than end-to-end models, the dominant approach for this task. Furthermore, we leverage the world knowledge of pretrained LMs, overcoming the limitation of previous layout-guided T2I works that can only handle predefined object classes. We demonstrate that our VPGen has improved control in counts/spatial relations/scales of objects than state-of-the-art T2I generation models. Second, we introduce VPEval, an interpretable and explainable evaluation framework for T2I generation based on visual programming. Unlike previous T2I evaluations with a single scoring model that is accurate in some skills but unreliable in others, VPEval produces evaluation programs that invoke a set of visual modules that are experts in different skills, and also provides visual+textual explanations of the evaluation results. Our analysis shows that VPEval provides a more human-correlated evaluation for skill-specific and open-ended prompts than widely used single model-based evaluation. We hope that our work encourages future progress on interpretable/explainable generation and evaluation for T2I models.

POSTER-69: FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations

Keywords: Graph Neural Networks Unsupervised Representation Learning Graph Filters

Scores: [ 5 3 6 6 ]

Unsupervised node representations learnt using contrastive learning-based methods have shown good performance on downstream tasks. However, these methods rely on augmentations that mimic low-pass filters, limiting their performance on tasks requiring different eigen-spectrum parts. This paper presents a simple filter-based augmentation method to capture different parts of the eigen-spectrum. We show significant improvements using these augmentations. Further, we show that sharing the same weights across these different filter augmentations is possible, reducing the computational load. In addition, previous works have shown that good performance on downstream tasks requires high dimensional representations. Working with high dimensions increases the computations, especially when multiple augmentations are involved. We mitigate this problem and recover good performance through lower dimensional embeddings using simple random Fourier feature projections. Our method, FiGURe, achieves an average gain of up to 4.4%, compared to the state-of-the-art unsupervised models, across all datasets in consideration, both homophilic and heterophilic. Our code can be found at:

SPOTLIGHT-9: Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

Keywords: Graph Neural Networks Conformal Prediction Uncertainty Quantification

Scores: [ 7 7 7 8 6 ]

Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data. However, GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is significant. We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates. Given an entity in the graph, CF-GNN produces a prediction set/interval that provably contains the true label with pre-defined coverage probability (e.g. 90%). We establish a permutation invariance condition that enables the validity of CP on graph data and provide an exact characterization of the test-time coverage. Moreover, besides valid coverage, it is crucial to reduce the prediction set size/interval length for practical use. We observe a key connection between non-conformity scores and network structures, which motivates us to develop a topology-aware output correction model that learns to update the prediction and produces more efficient prediction sets/intervals. Extensive experiments show that CF-GNN achieves any pre-defined target marginal coverage while significantly reducing the prediction set/interval size by up to 74% over the baselines. It also empirically achieves satisfactory conditional coverage over various raw and network features.

POSTER-70: A generative model of the hippocampal formation trained with theta driven local learning rules

Keywords: hippocampus path integration local learning generative models oscillations inference Helmholtz machine wake-sleep

Scores: [ 7 4 7 6 ]

Advances in generative models have recently revolutionised machine learning. Meanwhile, in neuroscience, generative models have long been thought fundamental to animal intelligence. Understanding the biological mechanisms that support these processes promises to shed light on the relationship between biological and artificial intelligence. In animals, the hippocampal formation is thought to learn and use a generative model to support its role in spatial and non-spatial memory. Here we introduce a biologically plausible model of the hippocampal formation tantamount to a Helmholtz machine that we apply to a temporal stream of inputs. A novel component of our model is that fast theta-band oscillations (5-10 Hz) gate the direction of information flow throughout the network, training it akin to a high-frequency wake-sleep algorithm. Our model accurately infers the latent state of high-dimensional sensory environments and generates realistic sensory predictions. Furthermore, it can learn to path integrate by developing a ring attractor connectivity structure matching previous theoretical proposals and flexibly transfer this structure between environments. Whereas many models trade-off biological plausibility with generality, our model captures a variety of hippocampal cognitive functions under one biologically plausible local learning rule.

POSTER-71: PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

Keywords: Pac-Bayes Adversarial Robustness Generalization

Scores: [ 4 7 6 5 ]

Deep neural networks (DNNs) are vulnerable to adversarial attacks. It is found empirically that adversarially robust generalization is crucial in establishing defense algorithms against adversarial attacks. Therefore, it is interesting to study the theoretical guarantee of robust generalization. This paper focuses on norm-based complexity, based on a PAC-Bayes approach (Neyshabur et al., 2017). The main challenge lies in extending the key ingredient, which is a weight perturbation bound in standard settings, to the robust settings. Existing attempts heavily rely on additional strong assumptions, leading to loose bounds. In this paper, we address this issue and provide a spectrally-normalized robust generalization bound for DNNs. Compared to existing bounds, our bound offers two significant advantages: Firstly, it does not depend on additional assumptions. Secondly, it is considerably tighter, aligning with the bounds of standard generalization. Therefore, our result provides a different perspective on understanding robust generalization: The mismatch terms between standard and robust generalization bounds shown in previous studies do not contribute to the poor robust generalization. Instead, these disparities solely due to mathematical issues. Finally, we extend the main result to adversarial robustness against general non-\(\ell_p\) attacks and other neural network architectures.

POSTER-72: Understanding the detrimental class-level effects of data augmentation

Keywords: data augmentation class-dependent bias

Scores: [ 6 7 7 4 ]

POSTER-73: Complexity of Derivative-Free Policy Optimization for Structured \(\mathcal{H}_\infty\) Control

Keywords: Structured \(\mathcal{H}_\infty\) Control Nonsmooth Optimization Complexity Analysis

Scores: [ 6 6 5 ]

The applications of direct policy search in reinforcement learning and continuous control have received increasing attention.In this work, we present novel theoretical results on the complexity of derivative-free policy optimization on an important class of robust control tasks, namely the structured \(H_\infty\) synthesis with static output feedback. Optimal \(H_\infty\) synthesis under structural constraints leads to a constrained nonconvex nonsmooth problem and is typicallyaddressed using subgradient-based policy search techniques that are built upon the concept of Goldstein subdifferential or other notions of enlarged subdifferential. In this paper, we study the complexity of finding \((\delta,\epsilon)\)-stationary points for such nonsmooth robust control design tasks using policy optimization methods which can only access the zeroth-order oracle (i.e. the \(H_\infty\) norm of the closed-loop system). First, we study the exact oracle setting and identify the coerciveness of the cost function to prove high-probability feasibility/complexity bounds for derivative-free policy optimization on this problem. Next, we derive a sample complexity result for the multi-input multi-output (MIMO) \(H_\infty\)-norm estimation. We combine this with our analysis to obtain the first sample complexity of model-free, trajectory-based, zeroth-order policy optimization on finding \((\delta,\epsilon)\)-stationary points for structured \(H_\infty\) control. Numerical results are also provided to demonstrate our theory.

POSTER-74: Star-Shaped Denoising Diffusion Probabilistic Models

Keywords: Generative models Diffusion Exponential Family

Scores: [ 8 6 5 7 8 6 ]

Denoising Diffusion Probabilistic Models (DDPMs) provide the foundation for the recent breakthroughs in generative modeling.Their Markovian structure makes it difficult to define DDPMs with distributions other than Gaussian or discrete.In this paper, we introduce Star-Shaped DDPM (SS-DDPM).Its star-shaped diffusion process allows us to bypass the need to define the transition probabilities or compute posteriors.We establish duality between star-shaped and specific Markovian diffusions for the exponential family of distributions and derive efficient algorithms for training and sampling from SS-DDPMs.In the case of Gaussian distributions, SS-DDPM is equivalent to DDPM.However, SS-DDPMs provide a simple recipe for designing diffusion models with distributions such as Beta, von Mises–Fisher, Dirichlet, Wishart and others, which can be especially useful when data lies on a constrained manifold.We evaluate the model in different settings and find it competitive even on image data, where Beta SS-DDPM achieves results comparable to a Gaussian DDPM.Our implementation is available at

POSTER-75: Diverse Shape Completion via Style Modulated Generative Adversarial Networks

Keywords: multimodal shape completion point cloud completion 3d shape generation generative modeling generative adversarial networks

Scores: [ 5 6 5 6 7 ]

Shape completion aims to recover the full 3D geometry of an object from a partial observation. This problem is inherently multi-modal since there can be many ways to plausibly complete the missing regions of a shape. Such diversity would be indicative of the underlying uncertainty of the shape and could be preferable for downstream tasks such as planning. In this paper, we propose a novel conditional generative adversarial network that can produce many diverse plausible completions of a partially observed point cloud. To enable our network to produce multiple completions for the same partial input, we introduce stochasticity into our network via style modulation. By extracting style codes from complete shapes during training, and learning a distribution over them, our style codes can explicitly carry shape category information leading to better completions. We further introduce diversity penalties and discriminators at multiple scales to prevent conditional mode collapse and to train without the need for multiple ground truth completions for each partial input. Evaluations across several synthetic and real datasets demonstrate that our method achieves significant improvements in respecting the partial observations while obtaining greater diversity in completions.

POSTER-76: PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

Keywords: Face Restoration Diffusion

Scores: [ 6 3 5 6 ]

Exploiting pre-trained diffusion models for restoration has recently become a favored alternative to the traditional task-specific training approach. Previous works have achieved noteworthy success by limiting the solution space using explicit degradation models. However, these methods often fall short when faced with complex degradations as they generally cannot be precisely modeled. In this paper, we introduce \(\textit{partial guidance}\), a fresh perspective that is more adaptable to real-world degradations compared to existing works. Rather than specifically defining the degradation process, our approach models the desired properties, such as image structure and color statistics of high-quality images, and applies this guidance during the reverse diffusion process. These properties are readily available and make no assumptions about the degradation process. When combined with a diffusion prior, this partial guidance can deliver appealing results across a range of restoration tasks. Additionally, our method can be extended to handle composite tasks by consolidating multiple high-quality image properties, achieved by integrating the guidance from respective tasks. Experimental results demonstrate that our method not only outperforms existing diffusion-prior-based approaches but also competes favorably with task-specific models.

POSTER-77: Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

Keywords: Sampling MCMC Conditional Mixing Non-log-concave Distributions

Scores: [ 7 7 6 7 ]

MCMC algorithms offer empirically efficient tools for sampling from a target distribution \(\pi(x) \propto \exp(-V(x))\). However, on the theory side, MCMC algorithms suffer from slow mixing rate when \(\pi(x)\) is non-log-concave. Our work examines this gap and shows that when Poincar'e-style inequality holds on a subset \(\mathcal{X}\) of the state space, the conditional distribution of MCMC iterates over \(\mathcal{X}\) mixes fast to the true conditional distribution. This fast mixing guarantee can hold in cases when global mixing is provably slow. We formalize the statement and quantify the conditional mixing rate. We further show that conditional mixing can have interesting implications for sampling from mixtures of Gaussians, parameter estimation for Gaussian mixture models, and Gibbs-sampling with well-connected local minima.

POSTER-78: Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

Keywords: Generalization algorithm stability multi-objective optimization gradient conflict

Scores: [ 5 6 4 7 ]

Multi-objective learning (MOL) often arises in emerging machine learning problems when multiple learning criteria or tasks need to be addressed. Recent works have developed various dynamic weighting algorithms for MOL, including MGDA and its variants, whose central idea is to find an update direction that avoids conflicts among objectives. Albeit its appealing intuition, empirical studies show that dynamic weighting methods may not always outperform static alternatives. To bridge this gap between theory and practice, we focus on a new variant of stochastic MGDA - the Multi-objective gradient with Double sampling (MoDo) algorithm and study its generalization performance and the interplay with optimization through the lens of algorithm stability. We find that the rationale behind MGDA -- updating along conflict-avoidant direction - may \emph{impede} dynamic weighting algorithms from achieving the optimal \({\cal O}(1/\sqrt{n})\) population risk, where \(n\) is the number of training samples. We further highlight the variability of dynamic weights and their impact on the three-way trade-off among optimization, generalization, and conflict avoidance that is unique in MOL. Code is available at

POSTER-79: Generalized Information-theoretic Multi-view Clustering

Keywords: information bottleneck multi-view clustering variational autoencoders

Scores: [ 6 6 6 4 ]

In an era of more diverse data modalities, multi-view clustering has become a fundamental tool for comprehensive data analysis and exploration. However, existing multi-view unsupervised learning methods often rely on strict assumptions on semantic consistency among samples. In this paper, we reformulate the multi-view clustering problem from an information-theoretic perspective and propose a general theoretical model. In particular, we define three desiderata under multi-view unsupervised learning in terms of mutual information, namely, comprehensiveness, concentration, and cross-diversity. The multi-view variational lower bound is then obtained by approximating the samples' high-dimensional mutual information. The Kullback–Leibler divergence is utilized to deduce sample assignments. Ultimately the information-based multi-view clustering model leverages deep neural networks and Stochastic Gradient Variational Bayes to achieve representation learning and clustering simultaneously. Extensive experiments on both synthetic and real datasets with wide types demonstrate that the proposed method exhibits a more stable and superior clustering performance than state-of-the-art algorithms.

SPOTLIGHT-10: Mechanism Design for Collaborative Normal Mean Estimation

Keywords: Mechanism design statistical minimax estimation federated learning

Scores: [ 6 6 7 6 7 8 ]

We study collaborative normal mean estimation, where \(m\) strategic agents collect i.i.d samples from a normal distribution \(\mathcal{N}(\mu, \sigma^2)\) at a cost. They all wish to estimate the mean \(\mu\). By sharing data with each other, agents can obtain better estimates while keeping the cost of data collection small. To facilitate this collaboration, we wish to design mechanisms that encourage agents to collect a sufficient amount of data and share it truthfully, so that they are all better off than working alone. In naive mechanisms, such as simply pooling and sharing all the data, an individual agent might find it beneficial to under-collect and/or fabricate data, which can lead to poor social outcomes. We design a novel mechanism that overcomes these challenges via two key techniques: first, when sharing the others' data with an agent, the mechanism corrupts this dataset proportional to how much the data reported by the agent differs from the others; second, we design minimax optimal estimators for the corrupted dataset. Our mechanism, which is Nash incentive compatible and individually rational, achieves a social penalty (sum of all agents' estimation errors and data collection costs) that is at most a factor 2 of the global minimum. When applied to high dimensional (non-Gaussian) distributions with bounded variance, this mechanism retains these three properties, but with slightly weaker results. Finally, in two special cases where we restrict the strategy space of the agents, we design mechanisms that essentially achieve the global minimum.

POSTER-80: Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift

Keywords: kernel methods covariate shift reproducing kernel Hilbert space (RKHS)

Scores: [ 7 7 6 5 ]

Covariate shift occurs prevalently in practice, where the input distributions of the source and target data are substantially different. Despite its practical importance in various learning problems, most of the existing methods only focus on some specific learning tasks and are not well validated theoretically and numerically. To tackle this problem, we propose a unified analysis of general nonparametric methods in a reproducing kernel Hilbert space (RKHS) under covariate shift. Our theoretical results are established for a general loss belonging to a rich loss function family, which includes many commonly used methods as special cases, such as mean regression, quantile regression, likelihood-based classification, and margin-based classification. Two types of covariate shift problems are the focus of this paper and the sharp convergence rates are established for a general loss function to provide a unified theoretical analysis, which concurs with the optimal results in literature where the squared loss is used. Extensive numerical studies on synthetic and real examples confirm our theoretical findings and further illustrate the effectiveness of our proposed method.

POSTER-81: HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Keywords: LLM ChatGPT Hugging Face Autonomous LLM

Scores: [ 6 7 9 6 3 ]

Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are numerous AI models available for various domains and modalities, they cannot handle complicated AI tasks autonomously. Considering large language models (LLMs) have exhibited exceptional abilities in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks, with language serving as a generic interface to empower this. Based on this philosophy, we present HuggingGPT, an LLM-powered agent that leverages LLMs (e.g., ChatGPT) to connect various AI models in machine learning communities (e.g., Hugging Face) to solve AI tasks. Specifically, we use ChatGPT to conduct task planning when receiving a user request, select models according to their function descriptions available in Hugging Face, execute each subtask with the selected AI model, and summarize the response according to the execution results. By leveraging the strong language capability of ChatGPT and abundant AI models in Hugging Face, HuggingGPT can tackle a wide range of sophisticated AI tasks spanning different modalities and domains and achieve impressive results in language, vision, speech, and other challenging tasks, which paves a new way towards the realization of artificial general intelligence.

POSTER-82: What Can We Learn from Unlearnable Datasets?

Keywords: data poisoning poisons unlearnable dataset data protection imperceptible perturbations adversarial machine learning

Scores: [ 7 4 4 7 ]

In an era of widespread web scraping, unlearnable dataset methods have the potential to protect data privacy by preventing deep neural networks from generalizing. But in addition to a number of practical limitations that make their use unlikely, we make a number of findings that call into question their ability to safeguard data. First, it is widely believed that neural networks trained on unlearnable datasets only learn shortcuts, simpler rules that are not useful for generalization. In contrast, we find that networks actually can learn useful features that can be reweighed for high test performance, suggesting that image protection is not assured. Unlearnable datasets are also believed to induce learning shortcuts through linear separability of added perturbations. We provide a counterexample, demonstrating that linear separability of perturbations is not a necessary condition. To emphasize why linearly separable perturbations should not be relied upon, we propose an orthogonal projection attack which allows learning from unlearnable datasets published in ICML 2021 and ICLR 2023. Our proposed attack is significantly less complex than recently proposed techniques.

POSTER-83: Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection

Keywords: Continual learning Class imbalance scalability Network intrusion detection and Cybersecurity

Scores: [ 6 4 6 ]

Intrusion detection is a form of anomalous activity detection in communication network traffic. Continual learning (CL) approaches to the intrusion detection task accumulate old knowledge while adapting to the latest threat knowledge. Previous works have shown the effectiveness of memory replay-based CL approaches for this task. In this work, we present two novel contributions to improve the performance of CL-based network intrusion detection in the context of class imbalance and scalability. First, we extend class balancing reservoir sampling (CBRS), a memory-based CL method, to address the problems of severe class imbalance for large datasets. Second, we propose a novel approach titled perturbation assistance for parameter approximation (PAPA) based on the Gaussian mixture model to reduce the number of \textit{virtual stochastic gradient descent (SGD) parameter} computations needed to discover maximally interfering samples for CL. We demonstrate that the proposed approaches perform remarkably better than the baselines on standard intrusion detection benchmarks created over shorter periods (KDDCUP'99, NSL-KDD, CICIDS-2017/2018, UNSW-NB15, and CTU-13) and a longer period with distribution shift (AnoShift). We also validated proposed approaches on standard continual learning benchmarks (SVHN, CIFAR-10/100, and CLEAR-10/100) and anomaly detection benchmarks (SMAP, SMD, and MSL). Further, the proposed PAPA approach significantly lowers the number of virtual SGD update operations, thus resulting in training time savings in the range of 12 to 40% compared to the maximally interfered samples retrieval algorithm.

SPOTLIGHT-11: Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

Keywords: Explainability Interpretability Time Series Explanations Temporal patterns Model Understanding Latent space Self-supervised learning

Scores: [ 5 7 7 6 7 ]

Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to an interpretable temporal pattern. While explainers from other modalities can be applied to time series, their inductive biases do not transfer well to the inherently challenging interpretation of time series. We present TimeX, a time series consistency model for training explainers. TimeX trains an interpretable surrogate to mimic the behavior of a pretrained time series model. It addresses the issue of model faithfulness by introducing model behavior consistency, a novel formulation that preserves relations in the latent space induced by the pretrained model with relations in the latent space induced by TimeX. TimeX provides discrete attribution maps and, unlike existing interpretability methods, it learns a latent space of explanations that can be used in various ways, such as to provide landmarks to visually aggregate similar explanations and easily recognize temporal patterns. We evaluate TimeX on eight synthetic and real-world datasets and compare its performance against state-of-the-art interpretability methods. We also conduct case studies using physiological time series. Quantitative evaluations demonstrate that TimeX achieves the highest or second-highest performance in every metric compared to baselines across all datasets. Through case studies, we show that the novel components of TimeX show potential for training faithful, interpretable models that capture the behavior of pretrained time series models.

SPOTLIGHT-12: Convergence of Adam Under Relaxed Assumptions

Keywords: Non-convex optimization Adam Convergence Variance reduction

Scores: [ 7 6 6 8 7 ]

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural networks, its theoretical properties are not yet fully understood, and existing convergence proofs require unrealistically strong assumptions, such as globally bounded gradients, to show the convergence to stationary points. In this paper, we show that Adam provably converges to \(\epsilon\)-stationary points with \(\mathcal{O}(\epsilon^{-4})\) gradient complexity under far more realistic conditions. The key to our analysis is a new proof of boundedness of gradients along the optimization trajectory of Adam, under a generalized smoothness assumption according to which the local smoothness (i.e., Hessian norm when it exists) is bounded by a sub-quadratic function of the gradient norm. Moreover, we propose a variance-reduced version of Adam with an accelerated gradient complexity of \(\mathcal{O}(\epsilon^{-3})\).

POSTER-84: Advancing Bayesian Optimization via Learning Correlated Latent Space

Keywords: Bayesian optimization smoothness regularization variational autoencoder

Scores: [ 4 3 4 7 ]

Bayesian optimization is a powerful method for optimizing black-box functions with limited function evaluations. Recent works have shown that optimization in a latent space through deep generative models such as variational autoencoders leads to effective and efficient Bayesian optimization for structured or discrete data. However, as the optimization does not take place in the input space, it leads to an inherent gap that results in potentially suboptimal solutions. To alleviate the discrepancy, we propose Correlated latent space Bayesian Optimization (CoBO), which focuses on learning correlated latent spaces characterized by a strong correlation between the distances in the latent space and the distances within the objective function. Specifically, our method introduces Lipschitz regularization, loss weighting, and trust region recoordination to minimize the inherent gap around the promising areas. We demonstrate the effectiveness of our approach on several optimization tasks in discrete data, such as molecule design and arithmetic expression fitting, and achieve high performance within a small budget.

POSTER-85: Closing the gap between the upper bound and lower bound of Adam's iteration complexity

Keywords: Adam Convergence Upper Bound Lower Bound

Scores: [ 3 7 6 5 ]

Recently, Arjevani et al. [1] establish a lower bound of iteration complexity for the first-order optimization under an \(L\)-smooth condition and a bounded noise variance assumption. However, a thorough review of existing literature on Adam's convergence reveals a noticeable gap: none of them meet the above lower bound. In this paper, we close the gap by deriving a new convergence guarantee of Adam, with only an \(L\)-smooth condition and a bounded noise variance assumption. Our results remain valid across a broad spectrum of hyperparameters. Especially with properly chosen hyperparameters, we derive an upper bound of the iteration complexity of Adam and show that it meets the lower bound for first-order optimizers. To the best of our knowledge, this is the first to establish such a tight upper bound for Adam's convergence. Our proof utilizes novel techniques to handle the entanglement between momentum and adaptive learning rate and to convert the first-order term in the Descent Lemma to the gradient norm, which may be of independent interest.

POSTER-86: Credal Marginal MAP

Keywords: graphical models credal networks probabilistic inference

Scores: [ 7 6 5 7 ]

Credal networks extend Bayesian networks to allow for imprecision in probability values. Marginal MAP is a widely applicable mixed inference task that identifies the most likely assignment for a subset of variables (called MAP variables). However, the task is extremely difficult to solve in credal networks particularly because the evaluation of each complete MAP assignment involves exact likelihood computations (combinatorial sums) over the vertices of a complex joint credal set representing the space of all possible marginal distributions of the MAP variables. In this paper, we explore Credal Marginal MAP inference and develop new exact methods based on variable elimination and depth-first search as well as several approximation schemes based on the mini-bucket partitioning and stochastic local search. An extensive empirical evaluation demonstrates the effectiveness of our new methods on random as well as real-world benchmark problems.

ORAL-1: Siamese Masked Autoencoders

Keywords: Representation Learning Visual Correspondence Self-supervised learning Videos

Scores: [ 7 6 7 7 7 ]

Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders (SiamMAE), a simple extension of Masked Autoencoders (MAE) for learning visual correspondence from videos. SiamMAE operates on pairs of randomly sampled video frames and asymmetrically masks them. These frames are processed independently by an encoder network, and a decoder composed of a sequence of cross-attention layers is tasked with predicting the missing patches in the future frame. By masking a large fraction (95%) of patches in the future frame while leaving the past frame unchanged, SiamMAE encourages the network to focus on object motion and learn object-centric representations. Despite its conceptual simplicity, features learned via SiamMAE outperform state-of-the-art self-supervised methods on video object segmentation, pose keypoint propagation, and semantic part propagation tasks. SiamMAE achieves competitive results without relying on data augmentation, handcrafted tracking-based pretext tasks, or other techniques to prevent representational collapse.

POSTER-87: Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective

Keywords: Adversarial Training

Scores: [ 4 6 7 6 ]

Adversarial Training (AT) has become arguably the state-of-the-art algorithm for extracting robust features. However, researchers recently notice that AT suffers from severe robust overfitting problems, particularly after learning rate (LR) decay. In this paper, we explain this phenomenon by viewing adversarial training as a dynamic minimax game between the model trainer and the attacker. Specifically, we analyze how LR decay breaks the balance between the minimax game by empowering the trainer with a stronger memorization ability, and show such imbalance induces robust overfitting as a result of memorizing non-robust features. We validate this understanding with extensive experiments, and provide a holistic view of robust overfitting from the dynamics of both the two game players. This understanding further inspires us to alleviate robust overfitting by rebalancing the two players by either regularizing the trainer's capacity or improving the attack strength. Experiments show that the proposed ReBalanced Adversarial Training (ReBAT) can attain good robustness and does not suffer from robust overfitting even after very long training. Code is available at

POSTER-88: Error Discovery By Clustering Influence Embeddings

Keywords: Debugging interpretability influence functions

Scores: [ 7 7 6 7 6 ]

We present a method for identifying groups of test examples---slices---on which a model under-performs, a task now known as slice discovery. We formalize coherence---a requirement that erroneous predictions, within a slice, should be wrong for the same reason---as a key property that any slice discovery method should satisfy. We then use influence functions to derive a new slice discovery method, InfEmbed, which satisfies coherence by returning slices whose examples are influenced similarly by the training data. InfEmbed is simple, and consists of applying K-Means clustering to a novel representation we deem influence embeddings. We show InfEmbed outperforms current state-of-the-art methods on 2 benchmarks, and is effective for model debugging across several case studies.

POSTER-89: Operation-Level Early Stopping for Robustifying Differentiable NAS

Keywords: Differentiable neural architecture search; Image classification; Failure of DARTS

Scores: [ 5 4 6 7 3 ]

Differentiable NAS (DARTS) is a simple and efficient neural architecture search method that has been extensively adopted in various machine learning tasks.% Nevertheless, DARTS still encounters several robustness issues, mainly the domination of skip connections.% The resulting architectures are full of parametric-free operations, leading to performance collapse.% Existing methods suggest that the skip connection has additional advantages in optimization compared to other parametric operations and propose to alleviate the domination of skip connections by eliminating these additional advantages.% In this paper, we analyze this issue from a simple and straightforward perspective and propose that the domination of skip connections results from parametric operations overfitting the training data while architecture parameters are trained on the validation data, leading to undesired behaviors.% Based on this observation, we propose the operation-level early stopping (OLES) method to overcome this issue and robustify DARTS without introducing any computation overhead.% Extensive experimental results can verify our hypothesis and the effectiveness of OLES.

POSTER-90: SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities

Keywords: Dimension Reduction Optimal Transport Affinities

Scores: [ 6 8 7 6 ]

ORAL-2: Private Everlasting Prediction

Keywords: Differential privacy private learning private prediction

Scores: [ 7 7 8 9 ]

A private learner is trained on a sample of labeled points and generates a hypothesis that can be used for predicting the labels of newly sampled points while protecting the privacy of the training set [Kasiviswannathan et al., FOCS 2008]. Past research uncovered that private learners may need to exhibit significantly higher sample complexity than non-private learners as is the case of learning of one-dimensional threshold functions [Bun et al., FOCS 2015, Alon et al., STOC 2019].We explore prediction as an alternative to learning. A predictor answers a stream of classification queries instead of outputting a hypothesis. Earlier work has considered a private prediction model with a single classification query [Dwork and Feldman, COLT 2018]. We observe that when answering a stream of queries, a predictor must modify the hypothesis it uses over time, and in a manner that cannot rely solely on the training set.We introduce {\em private everlasting prediction} taking into account the privacy of both the training set {\em and} the (adaptively chosen) queries made to the predictor. We then present a generic construction of private everlasting predictors in the PAC model.The sample complexity of the initial training sample in our construction is quadratic (up to polylog factors) in the VC dimension of the concept class. Our construction allows prediction for all concept classes with finite VC dimension, and in particular threshold functions over infinite domains, for which (traditional) private learning is known to be impossible.

POSTER-91: On the Importance of Exploration for Generalization in Reinforcement Learning

Keywords: reinforcement learning generalization procgen crafter

Scores: [ 4 7 5 5 7 ]

Existing approaches for improving generalization in deep reinforcement learning (RL) have mostly focused on representation learning, neglecting RL-specific aspects such as exploration. We hypothesize that the agent's exploration strategy plays a key role in its ability to generalize to new environments.Through a series of experiments in a tabular contextual MDP, we show that exploration is helpful not only for efficiently finding the optimal policy for the training environments but also for acquiring knowledge that helps decision making in unseen environments. Based on these observations, we propose EDE: Exploration via Distributional Ensemble, a method that encourages the exploration of states with high epistemic uncertainty through an ensemble of Q-value distributions. The proposed algorithm is the first value-based approach to achieve strong performance on both Procgen and Crafter, two benchmarks for generalization in RL with high-dimensional observations. The open-sourced implementation can be found at

POSTER-92: CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels

Keywords: Learning with Noisy Labels Optimal Transport Curriculum Learning

Scores: [ 6 5 6 7 5 ]

Learning with noisy labels (LNL) poses a significant challenge in training a well-generalized model while avoiding overfitting to corrupted labels.Recent advances have achieved impressive performance by identifying clean labels and correcting corrupted labels for training.However, the current approaches rely heavily on the model’s predictions and evaluate each sample independently without considering either the global or local structure of the sample distribution.These limitations typically result in a suboptimal solution for the identification and correction processes, which eventually leads to models overfitting to incorrect labels.In this paper, we propose a novel optimal transport (OT) formulation, called Curriculum and Structure-aware Optimal Transport (CSOT). CSOT concurrently considers the inter- and intra-distribution structure of the samples to construct a robust denoising and relabeling allocator.During the training process, the allocator incrementally assigns reliable labels to a fraction of the samples with the highest confidence. These labels have both global discriminability and local coherence.Notably, CSOT is a new OT formulation with a nonconvex objective function and curriculum constraints, so it is not directly compatible with classical OT solvers. Here, we develop a lightspeed computational method that involves a scaling iteration within a generalized conditional gradient framework to solve CSOT efficiently.Extensive experiments demonstrate the superiority of our method over the current state-of-the-arts in LNL.

POSTER-93: Learning Causal Models under Independent Changes

Keywords: independent mechanisms causal discovery information theory gaussian processes

Scores: [ 7 7 7 4 ]

In many scientific applications, we observe a system in different conditions in which its components may change, rather than in isolation. In our work, we are interested in explaining the generating process of such a multi-context system using a finite mixture of causal mechanisms. Recent work shows that this causal model is identifiable from data, but is limited to settings where the sparse mechanism shift hypothesis holds and only a subset of the causal conditionals change. As this assumption is not easily verifiable in practice, we study the more general principle that mechanism shifts are independent, which we formalize using the algorithmic notion of independence. We introduce an approach for causal discovery beyond partially directed graphs using Gaussian Process models, and give conditions under which we provably identify the correct causal model. In our experiments, we show that our method performs well in a range of synthetic settings, on realistic gene expression simulations, as well as on real-world cell signaling data.

SPOTLIGHT-13: WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

Keywords: long-range time series forecasting information transmission long- and short-term repetitive patterns global and local correlations

Scores: [ 5 7 5 8 ]

Capturing semantic information is crucial for accurate long-range time series forecasting, which involves modeling global and local correlations, as well as discovering long- and short-term repetitive patterns. Previous works have partially addressed these issues separately, but have not been able to address all of them simultaneously. Meanwhile, their time and memory complexities are still not sufficiently low for long-range forecasting. To address the challenge of capturing different types of semantic information, we propose a novel Water-wave Information Transmission (WIT) framework. This framework captures both long- and short-term repetitive patterns through bi-granular information transmission. It also models global and local correlations by recursively fusing and selecting information using Horizontal Vertical Gated Selective Unit (HVGSU). In addition, to improve the computing efficiency, we propose a generic Recurrent Acceleration Network (RAN) which reduces the time complexity to \(\mathcal{O}(\sqrt{L})\) while maintaining the memory complexity at \(\mathcal{O}(L)\). Our proposed method, called Water-wave Information Transmission and Recurrent Acceleration Network (WITRAN), outperforms the state-of-the-art methods by 5.80% and 14.28% on long-range and ultra-long-range time series forecasting tasks respectively, as demonstrated by experiments on four benchmark datasets. The code is available at:

POSTER-94: Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion

Keywords: Molecule Joint Auto-encoding Molecule Joint Self-supervised Learning Markov processes contrastive learning molecule representation learning

Scores: [ 5 6 5 6 ]

POSTER-95: Color Equivariant Convolutional Networks

Keywords: color equivariance equivariance color robustness equivariant convolutions

Scores: [ 5 6 6 5 ]

Color is a crucial visual cue readily exploited by Convolutional Neural Networks (CNNs) for object recognition. However, CNNs struggle if there is data imbalance between color variations introduced by accidental recording conditions. Color invariance addresses this issue but does so at the cost of removing all color information, which sacrifices discriminative power. In this paper, we propose Color Equivariant Convolutions (CEConvs), a novel deep learning building block that enables shape feature sharing across the color spectrum while retaining important color information. We extend the notion of equivariance from geometric to photometric transformations by incorporating parameter sharing over hue-shifts in a neural network. We demonstrate the benefits of CEConvs in terms of downstream performance to various tasks and improved robustness to color changes, including train-test distribution shifts. Our approach can be seamlessly integrated into existing architectures, such as ResNets, and offers a promising solution for addressing color-based domain shifts in CNNs.

POSTER-96: Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network

Keywords: Feature Interaction Search Deep Sparse Network

Scores: [ 5 4 6 6 ]

Deep sparse networks are widely investigated as a neural network architecture for prediction tasks with high-dimensional sparse features, with which feature interaction selection is a critical component. While previous methods primarily focus on how to search feature interaction in a coarse-grained space, less attention has been given to a finer granularity. In this work, we introduce a hybrid-grained feature interaction selection approach that targets both feature field and feature value for deep sparse networks. To explore such expansive space, we propose a decomposed space which is calculated on the fly. We then develop a selection algorithm called OptFeature, which efficiently selects the feature interaction from both the feature field and the feature value simultaneously. Results from experiments on three large real-world benchmark datasets demonstrate that OptFeature performs well in terms of accuracy and efficiency. Additional studies support the feasibility of our method. All source code are publicly available\footnote{}.

POSTER-97: BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

Keywords: time series forecasting basis learning self-supervised learning

Scores: [ 8 4 4 7 5 ]

Bases have become an integral part of modern deep learning-based models for time series forecasting due to their ability to act as feature extractors or future references. To be effective, a basis must be tailored to the specific set of time series data and exhibit distinct correlation with each time series within the set. However, current state-of-the-art methods are limited in their ability to satisfy both of these requirements simultaneously. To address this challenge, we propose BasisFormer, an end-to-end time series forecasting architecture that leverages learnable and interpretable bases. This architecture comprises three components: First, we acquire bases through adaptive self-supervised learning, which treats the historical and future sections of the time series as two distinct views and employs contrastive learning. Next, we design a Coef module that calculates the similarity coefficients between the time series and bases in the historical view via bidirectional cross-attention. Finally, we present a Forecast module that selects and consolidates the bases in the future view based on the similarity coefficients, resulting in accurate future predictions. Through extensive experiments on six datasets, we demonstrate that BasisFormer outperforms previous state-of-the-art methods by 11.04% and 15.78% respectively for univariate and multivariate forecasting tasks. Code isavailable at:

POSTER-98: Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction

Keywords: Medical Image Computed Tomography Metal Arftiacts Implicit Neural Representation Unsupervised Learning

Scores: [ 8 4 5 7 ]

Emerging neural reconstruction techniques based on tomography (e.g., NeRF, NeAT, and NeRP) have started showing unique capabilities in medical imaging. In this work, we present a novel Polychromatic neural representation (Polyner) to tackle the challenging problem of CT imaging when metallic implants exist within the human body. CT metal artifacts arise from the drastic variation of metal's attenuation coefficients at various energy levels of the X-ray spectrum, leading to a nonlinear metal effect in CT measurements. Recovering CT images from metal-affected measurements hence poses a complicated nonlinear inverse problem where empirical models adopted in previous metal artifact reduction (MAR) approaches lead to signal loss and strongly aliased reconstructions. Polyner instead models the MAR problem from a nonlinear inverse problem perspective. Specifically, we first derive a polychromatic forward model to accurately simulate the nonlinear CT acquisition process. Then, we incorporate our forward model into the implicit neural representation to accomplish reconstruction. Lastly, we adopt a regularizer to preserve the physical properties of the CT images across different energy levels while effectively constraining the solution space. Our Polyner is an unsupervised method and does not require any external training data. Experimenting with multiple datasets shows that our Polyner achieves comparable or better performance than supervised methods on in-domain datasets while demonstrating significant performance improvements on out-of-domain datasets. To the best of our knowledge, our Polyner is the first unsupervised MAR method that outperforms its supervised counterparts. The code for this work is available at:

POSTER-99: Personalized Dictionary Learning for Heterogeneous Datasets

Keywords: Dictionary Learning Data Heterogeneity Personalization

Scores: [ 4 6 6 7 ]

We introduce a relevant yet challenging problem named Personalized Dictionary Learning (PerDL), where the goal is to learn sparse linear representations from heterogeneous datasets that share some commonality. In PerDL, we model each dataset's shared and unique features as global and local dictionaries. Challenges for PerDL not only are inherited from classical dictionary learning(DL), but also arise due to the unknown nature of the shared and unique features. In this paper, we rigorously formulate this problem and provide conditions under which the global and local dictionaries can be provably disentangled. Under these conditions, we provide a meta-algorithm called Personalized Matching and Averaging (PerMA) that can recover both global and local dictionaries from heterogeneous datasets. PerMA is highly efficient; it converges to the ground truth at a linear rate under suitable conditions. Moreover, it automatically borrows strength from strong learners to improve the prediction of weak learners. As a general framework for extracting global and local dictionaries, we show the application of PerDL in different learning tasks, such as training with imbalanced datasets and video surveillance.

POSTER-100: TIES-Merging: Resolving Interference When Merging Models

Keywords: Model Merging Fusing Collaborative Training Robust Fine-tuning Federated Learning

Scores: [ 6 6 5 7 6 ]

Transfer learning – i.e., further fine-tuning a pre-trained model on a downstream task – can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have led to a proliferation of task-specific fine-tuned models, which typically can only perform a single task and do not benefit from one another. Recently, model merging techniques have emerged as a solution to combine multiple task-specific models into a single multitask model without performing additional training. However, existing merging methods often ignore the interference between parameters of different models, resulting in large performance drops when merging multiple models. In this paper, we demonstrate that prior merging techniques inadvertently lose valuable information due to two major sources of interference: (a) interference due to redundant parameter values and (b) disagreement on the sign of a given parameter’s values across models. To address this, we propose our method, TrIm, Elect Sign & Merge (TIES-Merging), which introduces three novel steps when merging models: (1) resetting parameters that only changed a small amount during fine-tuning, (2) resolving sign conflicts, and (3) merging only the parameters that are in alignment with the final agreed-upon sign. We find that TIES-Merging outperforms existing methods in diverse settings covering a range of modalities, domains, number of tasks, model sizes, architectures, and fine-tuning settings. We further analyze the impact of different types of interference on model parameters, highlight the importance of signs, and show that estimating the signs using the validation data could further improve performance.

POSTER-101: Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case

Keywords: algorithms with predictions beyond the worst-case analysis of algorithms time complexity combinatorial optimization discrete convex analysis submodular functions

Scores: [ 5 6 7 5 7 5 ]

Recent years have seen a growing interest in accelerating optimization algorithms with machine-learned predictions. Sakaue and Oki (NeurIPS 2022) have developed a general framework that warm-starts the L-convex function minimization method with predictions, revealing the idea's usefulness for various discrete optimization problems. In this paper, we present a framework for using predictions to accelerate M-convex function minimization, thus complementing previous research and extending the range of discrete optimization algorithms that can benefit from predictions. Our framework is particularly effective for an important subclass called laminar convex minimization, which appears in many operations research applications. Our methods can improve time complexity bounds upon the best worst-case results by using predictions and even have potential to go beyond a lower-bound result.

SPOTLIGHT-14: Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

Keywords: adversarial robustness graph neural networks

Scores: [ 7 7 5 6 ]

Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those that affect both node features and graph topology. This paper investigates GNNs derived from diverse neural flows, concentrating on their connection to various stability notions such as BIBO stability, Lyapunov stability, structural stability, and conservative stability. We argue that Lyapunov stability, despite its common use, does not necessarily ensure adversarial robustness. Inspired by physics principles, we advocate for the use of conservative Hamiltonian neural flows to construct GNNs that are robust to adversarial attacks. The adversarial robustness of different neural flow GNNs is empirically compared on several benchmark datasets under a variety of adversarial attacks. Extensive numerical experiments demonstrate that GNNs leveraging conservative Hamiltonian flows with Lyapunov stability substantially improve robustness against adversarial perturbations. The implementation code of experiments is available at \url{}.

SPOTLIGHT-15: QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Keywords: Quantization Large Language Models Adaptive Rounding Theoretical Guarantees

Scores: [ 7 5 7 7 ]

This work studies post-training parameter quantization in large language models (LLMs). We introduce quantization with incoherence processing (QuIP), a new method based on the insight that quantization benefits from incoherent weight and Hessian matrices, i.e., from the weights being even in magnitude and the directions in which it is important to round them accurately being unaligned with the coordinate axes. QuIP consists of two steps: (1) an adaptive rounding procedure minimizing a quadratic proxy objective; (2) efficient pre- and post-processing that ensures weight and Hessian incoherence via multiplication by random orthogonal matrices. We complement QuIP with the first theoretical analysis for an LLM-scale quantization algorithm, and show that our theory also applies to an existing method, OPTQ. Empirically, we find that our incoherence preprocessing improves several existing quantization algorithms and yields the first LLM quantization methods that produce viable results using only two bits per weight. Our code can be found at

POSTER-102: FaceComposer: A Unified Model for Versatile Facial Content Creation

Keywords: diffusion model; talking face generation; face generation

Scores: [ 7 5 6 5 ]

This work presents FaceComposer, a unified generative model that accomplishes a variety of facial content creation tasks, including text-conditioned face synthesis, text-guided face editing, face animation etc. Based on the latent diffusion framework, FaceComposer follows the paradigm of compositional generation and employs diverse face-specific conditions, e.g., Identity Feature and Projected Normalized Coordinate Code, to release the model creativity at all possible. To support text control and animation, we clean up some existing face image datasets and collect around 500 hours of talking-face videos, forming a high-quality large-scale multi-modal face database. A temporal self-attention module is incorporated into the U-Net structure, which allows learning the denoising process on the mixture of images and videos. Extensive experiments suggest that our approach not only achieves comparable or even better performance than state-of-the-arts on each single task, but also facilitates some combined tasks with one-time forward, demonstrating its potential in serving as a foundation generative model in face domain. We further develop an interface such that users can enjoy our one-step service to create, edit, and animate their own characters. Code, dataset, model, and interface will be made publicly available.

POSTER-103: Calibrating “Cheap Signals” in Peer Review without a Prior

Keywords: Peer prediction Peer review Calibration

Scores: [ 5 7 5 4 5 ]

Peer review lies at the core of the academic process, but even well-intentioned reviewers can still provide noisy ratings. While ranking papers by average ratings may reduce noise, varying noise levels and systematic biases stemming from ``cheap'' signals (e.g. author identity, proof length) can lead to unfairness. Detecting and correcting bias is challenging, as ratings are subjective and unverifiable. Unlike previous works relying on prior knowledge or historical data, we propose a one-shot noise calibration process without any prior information. We ask reviewers to predict others' scores and use these predictions for calibration. Assuming reviewers adjust their predictions according to the noise, we demonstrate that the calibrated score results in a more robust ranking compared to average ratings, even with varying noise levels and biases.In detail, we show that the error probability of the calibrated score approaches zero as the number of reviewers increases and is significantly lower compared to average ratings when the number of reviewers is small.

POSTER-104: Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation

Keywords: Uncertainty estimation multimodality neural processes

Scores: [ 6 6 7 5 6 ]

Uncertainty estimation is an important research area to make deep neural networks (DNNs) more trustworthy. While extensive research on uncertainty estimation has been conducted with unimodal data, uncertainty estimation for multimodal data remains a challenge. Neural processes (NPs) have been demonstrated to be an effective uncertainty estimation method for unimodal data by providing the reliability of Gaussian processes with efficient and powerful DNNs. While NPs hold significant potential for multimodal uncertainty estimation, the adaptation of NPs for multimodal data has not been carefully studied. To bridge this gap, we propose Multimodal Neural Processes (MNPs) by generalising NPs for multimodal uncertainty estimation. Based on the framework of NPs, MNPs consist of several novel and principled mechanisms tailored to the characteristics of multimodal data. In extensive empirical evaluation, our method achieves state-of-the-art multimodal uncertainty estimation performance, showing its appealing robustness against noisy samples and reliability in out-of-distribution detection with faster computation time compared to the current state-of-the-art multimodal uncertainty estimation method.

POSTER-105: StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

Keywords: representation learning synthetic images text-to-image models

Scores: [ 8 7 7 7 5 ]

We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural question in the light of the excellent performance of such models in generating high-quality images. We consider specifically the Stable Diffusion, one of the leading open source text-to-image models. We show that (1) when the generative model is properly configured, training self-supervised methods on synthetic images can match or beat the real image counterpart;(2) by treating the multiple images generated from the same text prompt as positives for each other, we develop a multi-positive contrastive learning method, which we call StableRep. With solely synthetic images, the representations learned by StableRep surpass the performance of representations learned by SimCLR and CLIP using the same set of text prompts and corresponding real images, on large scale datasets. When we further add language supervision, \name~trained with 20M synthetic images (10M captions) achieves better accuracy than CLIP trained with 50M real images (50M captions).

POSTER-106: Fitting trees to \(\ell_1\)-hyperbolic distances

Keywords: tree metric fitting ultrametric fitting \(\ell_1\)-hyperbolicity

Scores: [ 6 6 5 5 ]

POSTER-107: Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Keywords: Conditional 3D Shape Generation Neural 3D Representation 3D Reconstruction

Scores: [ 5 6 5 6 ]

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to 3D shapes is prone to producing inconsistent results with the conditions because 3D shapes have an additional dimension whose distribution significantly differs from that of 2D images and texts. To bridge the domain gap among the three modalities and facilitate multi-modal-conditioned 3D shape generation, we explore representing 3D shapes in a shape-image-text-aligned space. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM). The former model encodes the 3D shapes into the shape latent space aligned to the image and text and reconstructs the fine-grained 3D neural fields corresponding to given shape embeddings via the transformer-based decoder. The latter model learns a probabilistic mapping function from the image or text space to the latent shape space. Our extensive experiments demonstrate that our proposed approach can generate higher-quality and more diverse 3D shapes that better semantically conform to the visual or textural conditional inputs, validating the effectiveness of the shape-image-text-aligned space for cross-modality 3D shape generation.

POSTER-108: Text Alignment Is An Efficient Unified Model for Massive NLP Tasks

Keywords: Text Alignment Efficient Unified Model NLU Tasks Factual Consistency Evaluation QA with Unanswerable Question

Scores: [ 7 4 7 5 ]

Large language models (LLMs), typically designed as a function of next-word prediction, have excelled across extensive NLP tasks. Despite the generality, next-word prediction is often not an efficient formulation for many of the tasks, demanding an extreme scale of model parameters (10s or 100s of billions) and sometimes yielding suboptimal performance.In practice, it is often desirable to build more efficient models---despite being less versatile, they still apply to a substantial subset of problems, delivering on par or even superior performance with much smaller model sizes.In this paper, we propose text alignment as an efficient unified model for a wide range of crucial tasks involving text entailment, similarity, question answering (and answerability), factual consistency, and so forth. Given a pair of texts, the model measures the degree of alignment between their information. We instantiate an alignment model through lightweight finetuning of RoBERTa (355M parameters) using 5.9M examples from 28 datasets. Despite its compact size, extensive experiments show the model's efficiency and strong performance: (1) On over 20 datasets of aforementioned diverse tasks, the model matches or surpasses FLAN-T5 models that have around 2x or 10x more parameters; the single unified model also outperforms task-specific models finetuned on individual datasets; (2) When applied to evaluate factual consistency of language generation on 23 datasets, our model improves over various baselines, including the much larger GPT-3.5 (ChatGPT) and sometimes even GPT-4; (3) The lightweight model can also serve as an add-on component for LLMs such as GPT-3.5 in question answering tasks, improving the average exact match (EM) score by 17.94 and F1 score by 15.05 through identifying unanswerable questions.

POSTER-109: Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression

Keywords: asymptotics random features model Bayesian inference

Scores: [ 5 6 5 6 ]

In this paper we compare and contrast the behavior of the posterior predictive distribution to the risk of the the maximum a posteriori estimator for the random features regression model in the overparameterized regime. We will focus on the variance of the posterior predictive distribution (Bayesian model average) and compare its asymptotics to that of the risk of the MAP estimator. In the regime where the model dimensions grow faster than any constant multiple of the number of samples, asymptotic agreement between these two quantities is governed by the phase transition in the signal-to-noise ratio. They also asymptotically agree with each other when the number of samples grow faster than any constant multiple of model dimensions. Numerical simulations illustrate finer distributional properties of the two quantities for finite dimensions. We conjecture they have Gaussian fluctuations and exhibit similar properties as found by previous authors in a Gaussian sequence model, this is of independent theoretical interest.

POSTER-110: Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs

Keywords: implicit bias implicit regularization training dynamics ReLU networks gradient flow theoretical analysis

Scores: [ 7 6 6 6 ]

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise the rank of network parameters. By assuming that the training points are correlated with the teacher neuron, we complement previous work that considered orthogonal datasets. Our results are based on a detailed non-asymptotic analysis of the dynamics of each hidden neuron throughout the training. We also show and characterise a surprising distinction in this setting between interpolator networks of minimal rank and those of minimal Euclidean norm. Finally we perform a range of numerical experiments, which corroborate our theoretical findings.

POSTER-111: Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks

Keywords: learning curve extrapolation prior-data fitted networks transformers Bayesian inference uncertainty estimation model selection

Scores: [ 7 5 6 7 ]

Learning curve extrapolation aims to predict model performance in later epochs of training, based on the performance in earlier epochs.In this work, we argue that, while the inherent uncertainty in the extrapolation of learning curves warrants a Bayesian approach, existing methods are (i) overly restrictive, and/or (ii) computationally expensive. We describe the first application of prior-data fitted neural networks (PFNs) in this context. A PFN is a transformer, pre-trained on data generated from a prior, to perform approximate Bayesian inference in a single forward pass. We propose LC-PFN, a PFN trained to extrapolate 10 million artificial right-censored learning curves generated from a parametric prior proposed in prior art using MCMC. We demonstrate that LC-PFN can approximate the posterior predictive distribution more accurately than MCMC, while being over 10 000 times faster. We also show that the same LC-PFN achieves competitive performance extrapolating a total of 20 000 real learning curves from four learning curve benchmarks (LCBench, NAS-Bench-201, Taskset, and PD1) that stem from training a wide range of model architectures (MLPs, CNNs, RNNs, and Transformers) on 53 different datasets with varying input modalities (tabular, image, text, and protein data). Finally, we investigate its potential in the context of model selection and find that a simple LC-PFN based predictive early stopping criterion obtains 2 - 6x speed-ups on 45 of these datasets, at virtually no overhead.

POSTER-112: Physics-Informed Bayesian Optimization of Variational Quantum Circuits

Keywords: Bayesian optimization Expected improvement Quantum computing Variational Quantum Eigensolvers

Scores: [ 6 5 7 6 ]

In this paper, we propose a novel and powerful method to harness Bayesian optimization for variational quantum eigensolvers (VQEs) - a hybrid quantum-classical protocol used to approximate the ground state of a quantum Hamiltonian. Specifically, we derive a VQE-kernel which incorporates important prior information about quantum circuits: the kernel feature map of the VQE-kernel exactly matches the known functional form of the VQE's objective function and thereby significantly reduces the posterior uncertainty.Moreover, we propose a novel acquisition function for Bayesian optimization called \emph{Expected Maximum Improvement over Confident Regions} (EMICoRe) which can actively exploit the inductive bias of the VQE-kernel by treating regions with low predictive uncertainty as indirectly "observed". As a result, observations at as few as three points in the search domain are sufficient to determine the complete objective function along an entire one-dimensional subspace of the optimization landscape. Our numerical experiments demonstrate that our approach improves over state-of-the-art baselines.

POSTER-113: Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

Keywords: reinforcement learning context variables symbolic policy

Scores: [ 5 6 5 7 ]

Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to understand and deploy with limited computational resources. Currently, employing compact symbolic expressions as symbolic policies is a promising strategy to obtain simple and interpretable policies. Previous symbolic policy methods usually involve complex training processes and pre-trained neural network policies, which are inefficient and limit the application of symbolic policies. In this paper, we propose an efficient gradient-based learning method named Efficient Symbolic Policy Learning (ESPL) that learns the symbolic policy from scratch in an end-to-end way. We introduce a symbolic network as the search space and employ a path selector to find the compact symbolic policy. By doing so we represent the policy with a differentiable symbolic expression and train it in an off-policy manner which further improves the efficiency. In addition, in contrast with previous symbolic policies which only work in single-task RL because of complexity, we expand ESPL on meta-RL to generate symbolic policies for unseen tasks. Experimentally, we show that our approach generates symbolic policies with higher performance and greatly improves data efficiency for single-task RL. In meta-RL, we demonstrate that compared with neural network policies the proposed symbolic policy achieves higher performance and efficiency and shows the potential to be interpretable.

POSTER-114: Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?

Keywords: Pruning Neural Network Sparsity Neural Architecture Search

Scores: [ 6 6 6 6 5 ]

Pruning at initialization (PaI) aims to remove weights of neural networks before training in pursuit of training efficiency besides the inference. While off-the-shelf PaI methods manage to find trainable subnetworks that outperform random pruning, their performance in terms of both accuracy and computational reduction is far from satisfactory compared to post-training pruning and the understanding of PaI is missing. For instance, recent studies show that existing PaI methods only able to find good layerwise sparsities not weights, as the discovered subnetworks are surprisingly resilient against layerwise random mask shuffling and weight re-initialization.In this paper, we study PaI from a brand-new perspective -- the topology of subnetworks. In particular, we propose a principled framework for analyzing the performance of Pruning and Initialization (PaI) methods with two quantities, namely, the number of effective paths and effective nodes. These quantities allow for a more comprehensive understanding of PaI methods, giving us an accurate assessment of different subnetworks at initialization. We systematically analyze the behavior of various PaI methods through our framework and observe a guiding principle for constructing effective subnetworks: *at a specific sparsity, the top-performing subnetwork always presents a good balance between the number of effective nodes and the number of effective paths.*Inspired by this observation, we present a novel data-agnostic pruning method by solving a multi-objective optimization problem. By conducting extensive experiments across different architectures and datasets, our results demonstrate that our approach outperforms state-of-the-art PaI methods while it is able to discover subnetworks that have much lower inference FLOPs (up to 3.4$\times$). Code will be fully released.

POSTER-115: Adversarial Resilience in Sequential Prediction via Abstention

Keywords: Sequential prediction adversarial examples abstention out-of-distribution VC Classes

Scores: [ 6 6 5 5 ]

We study the problem of sequential prediction in the stochastic setting with an adversary that is allowed to inject clean-label adversarial (or out-of-distribution) examples. Algorithms designed to handle purely stochastic data tend to fail in the presence of such adversarial examples, often leading to erroneous predictions. This is undesirable in many high-stakes applications such as medical recommendations, where abstaining from predictions on adversarial examples is preferable to misclassification. On the other hand, assuming fully adversarial data leads to very pessimistic bounds that are often vacuous in practice. To move away from these pessimistic guarantees, we propose a new model of sequential prediction that sits between the purely stochastic and fully adversarial settings by allowing the learner to abstain from making a prediction at no cost on adversarial examples, thereby asking the learner to make predictions with certainty. Assuming access to the marginal distribution on the non-adversarial examples, we design a learner whose error scales with the VC dimension (mirroring the stochastic setting) of the hypothesis class, as opposed to the Littlestone dimension which characterizes the fully adversarial setting. Furthermore, we design learners for VC dimension~1 classes and the class of axis-aligned rectangles, which work even in the absence of access to the marginal distribution. Our key technical contribution is a novel measure for quantifying uncertainty for learning VC classes, which may be of independent interest.

POSTER-116: On Evaluating Adversarial Robustness of Large Vision-Language Models

Keywords: Large Vision-Language Models Adversarial Robustness

Scores: [ 7 6 7 7 ]

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT. Nonetheless, multimodal generation exacerbates safety concerns, since adversaries may successfully evade the entire system by subtly manipulating the most vulnerable modality (e.g., vision). To this end, we propose evaluating the robustness of open-source large VLMs in the most realistic and high-risk setting, where adversaries have only black-box system access and seek to deceive the model into returning the targeted responses. In particular, we first craft targeted adversarial examples against pretrained models such as CLIP and BLIP, and then transfer these adversarial examples to other VLMs such as MiniGPT-4, LLaVA, UniDiffuser, BLIP-2, and Img2Prompt. In addition, we observe that black-box queries on these VLMs can further improve the effectiveness of targeted evasion, resulting in a surprisingly high success rate for generating targeted responses. Our findings provide a quantitative understanding regarding the adversarial vulnerability of large VLMs and call for a more thorough examination of their potential security flaws before deployment in practice. Our project page:

POSTER-117: Practical Equivariances via Relational Conditional Neural Processes

Keywords: neural processes equivariance Gaussian processes

Scores: [ 2 7 8 6 ]

POSTER-118: For SALE: State-Action Representation Learning for Deep Reinforcement Learning

Keywords: Deep reinforcement learning representation learning

Scores: [ 6 7 7 7 5 ]

In reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states. We extensively study the design space of these embeddings and highlight important design considerations. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 algorithm, which significantly outperforms existing continuous control algorithms. On OpenAI gym benchmark tasks, TD7 has an average performance gain of 276.7% and 50.7% over TD3 at 300k and 5M time steps, respectively, and works in both the online and offline settings.

POSTER-119: Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles

Keywords: ridge regression ensembling methods

Scores: [ 7 5 5 5 6 ]

Feature bagging is a well-established ensembling method which aims to reduceprediction variance by combining predictions of many estimators trained on subsetsor projections of features. Here, we develop a theory of feature-bagging in noisyleast-squares ridge ensembles and simplify the resulting learning curves in the specialcase of equicorrelated data. Using analytical learning curves, we demonstratethat subsampling shifts the double-descent peak of a linear predictor. This leadsus to introduce heterogeneous feature ensembling, with estimators built on varyingnumbers of feature dimensions, as a computationally efficient method to mitigatedouble-descent. Then, we compare the performance of a feature-subsamplingensemble to a single linear predictor, describing a trade-off between noise amplificationdue to subsampling and noise reduction due to ensembling. Our qualitativeinsights carry over to linear classifiers applied to image classification tasks withrealistic datasets constructed using a state-of-the-art deep learning feature map.

POSTER-120: Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy

Keywords: Data Pruning Data Subset Selection Noisy Labels Relabeling Self-training

Scores: [ 6 5 5 7 ]

Data pruning, which aims to downsize a large training set into a small informative subset, is crucial for reducing the enormous computational costs of modern deep learning. Though large-scale data collections invariably contain annotation noise and numerous robust learning methods have been developed, data pruning for the noise-robust learning scenario has received little attention. With state-of-the-art Re-labeling methods that self-correct erroneous labels while training, it is challenging to identify which subset induces the most accurate re-labeling of erroneous labels in the entire training set. In this paper, we formalize the problem of data pruning with re-labeling. We first show that the likelihood of a training example being correctly re-labeled is proportional to the prediction confidence of its neighborhood in the subset. Therefore, we propose a novel data pruning algorithm, Prune4Rel, that finds a subset maximizing the total neighborhood confidence of all training examples, thereby maximizing the re-labeling accuracy and generalization performance. Extensive experiments on four real and one synthetic noisy datasets show that Prune4Rel outperforms the baselines with Re-labeling models by up to 9.1% as well as those with a standard model by up to 21.6%.

POSTER-121: Fair Graph Distillation

Keywords: Graph Distillation Algorithmic Fairness

Scores: [ 6 5 7 5 ]

As graph neural networks (GNNs) struggle with large-scale graphs due to high computational demands, data distillation for graph data promises to alleviate this issue by distilling a large real graph into a smaller distilled graph while maintaining comparable prediction performance for GNNs trained on both graphs. However, we observe that GNNs trained on distilled graphs may exhibit more severe group fairness problems than those trained on real graphs. Motivated by this observation, we propose \textit{fair graph distillation} (\Algnameabbr), an approach for generating small distilled \textit{fair and informative} graphs based on the graph distillation method. The challenge lies in the deficiency of sensitive attributes for nodes in the distilled graph, making most debiasing methods (e.g., regularization and adversarial debiasing) intractable for distilled graphs. We develop a simple yet effective bias metric, called coherence, for distilled graphs. Based on the proposed coherence metric, we introduce a framework for fair graph distillation using a bi-level optimization algorithm. Extensive experiments demonstrate that the proposed algorithm can achieve better prediction performance-fairness trade-offs across various datasets and GNN architectures.

POSTER-122: Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?

Keywords: Recommender system Mechanism design Potential function Optimization

Scores: [ 5 8 6 6 ]

The past decade has witnessed the flourishing of a new profession as media content creators, who rely on revenue streams from online content recommendation platforms. The reward mechanism employed by these platforms creates a competitive environment among creators which affects their production choices and, consequently, content distribution and system welfare. It is thus crucial to design the platform's reward mechanism in order to steer the creators' competition towards a desirable welfare outcome in the long run. This work makes two major contributions in this regard: first, we uncover a fundamental limit about a class of widely adopted mechanisms, coined \emph{Merit-based Monotone Mechanisms}, by showing that they inevitably lead to a constant fraction loss of the optimal welfare. To circumvent this limitation, we introduce \emph{Backward Rewarding Mechanisms} (BRMs) and show that the competition game resultant from BRMs possesses a potential game structure. BRMs thus naturally induce strategic creators' collective behaviors towards optimizing the potential function, which can be designed to match any given welfare metric. In addition, the class of BRM can be parameterized so that it allows the platform to directly optimize welfare within the feasible mechanism space even when the welfare metric is not explicitly defined.

POSTER-123: Compact Neural Volumetric Video Representations with Dynamic Codebooks

Keywords: Computer Vision 3D Vision Volumetric Video

Scores: [ 7 6 4 7 3 ]

This paper addresses the challenge of representing high-fidelity volumetric videos with low storage cost. Some recent feature grid-based methods have shown superior performance of fast learning implicit neural representations from input 2D images. However, such explicit representations easily lead to large model sizes when modeling dynamic scenes. To solve this problem, our key idea is reducing the spatial and temporal redundancy of feature grids, which intrinsically exist due to the self-similarity of scenes. To this end, we propose a novel neural representation, named dynamic codebook, which first merges similar features for the model compression and then compensates for the potential decline in rendering quality by a set of dynamic codes. Experiments on the NHR and DyNeRF datasets demonstrate that the proposed approach achieves state-of-the-art rendering quality, while being able to achieve more storage efficiency. The source code is available at

POSTER-124: Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

Keywords: Text-driven Motion Synthesis Diffusion Models Graph networks

Scores: [ 6 6 5 6 ]

Most text-driven human motion generation methods employ sequential modeling approaches, e.g., transformer, to extract sentence-level text representations automatically and implicitly for human motion synthesis. However, these compact text representations may overemphasize the action names at the expense of other important properties and lack fine-grained details to guide the synthesis of subtly distinct motion. In this paper, we propose hierarchical semantic graphs for fine-grained control over motion generation. Specifically, we disentangle motion descriptions into hierarchical semantic graphs including three levels of motions, actions, and specifics. Such global-to-local structures facilitate a comprehensive understanding of motion description and fine-grained control of motion generation. Correspondingly, to leverage the coarse-to-fine topology of hierarchical semantic graphs, we decompose the text-to-motion diffusion process into three semantic levels, which correspond to capturing the overall motion, local actions, and action specifics. Extensive experiments on two benchmark human motion datasets, including HumanML3D and KIT, with superior performances, justify the efficacy of our method. More encouragingly, by modifying the edge weights of hierarchical semantic graphs, our method can continuously refine the generated motion, which may have a far-reaching impact on the community. Code and pre-trained weights are available at

SPOTLIGHT-16: Robust Model Reasoning and Fitting via Dual Sparsity Pursuit

Keywords: Model reasoning; Model fitting; Outliers; Sparse subspace learning; Feature matching

Scores: [ 8 6 6 8 7 ]

In this paper, we contribute to solving a threefold problem: outlier rejection, true model reasoning and parameter estimation with a unified optimization modeling. To this end, we first pose this task as a sparse subspace recovering problem, to search a maximum of independent bases under an over-embedded data space. Then we convert the objective into a continuous optimization paradigm that estimates sparse solutions for both bases and errors. Wherein a fast and robust solver is proposed to accurately estimate the sparse subspace parameters and error entries, which is implemented by a proximal approximation method under the alternating optimization framework with the ``optimal'' sub-gradient descent. Extensive experiments regarding known and unknown model fitting on synthetic and challenging real datasets have demonstrated the superiority of our method against the state-of-the-art. We also apply our method to multi-class multi-model fitting and loop closure detection, and achieve promising results both in accuracy and efficiency. Code is released at:

POSTER-125: The Tunnel Effect: Building Data Representations in Deep Neural Networks

Keywords: representation learning continual learning training dynamics

Scores: [ 6 7 3 6 ]

Deep neural networks are widely known for their remarkable effectiveness across various tasks, with the consensus that deeper networks implicitly learn more complex data representations. This paper shows that sufficiently deep networks trained for supervised image classification split into two distinct parts that contribute to the resulting data representations differently. The initial layers create linearly-separable representations, while the subsequent layers, which we refer to as \textit{the tunnel}, compress these representations and have a minimal impact on the overall performance. We explore the tunnel's behavior through comprehensive empirical studies, highlighting that it emerges early in the training process. Its depth depends on the relation between the network's capacity and task complexity. Furthermore, we show that the tunnel degrades out-of-distribution generalization and discuss its implications for continual learning.

POSTER-126: Stability of Random Forests and Coverage of Random-Forest Prediction Intervals

Keywords: Stability Prediction Intervals Random Forests

Scores: [ 2 7 6 8 ]

POSTER-127: Learning DAGs from Data with Few Root Causes

Keywords: directed acyclic graph few root causes structural equation models linear SEMs additive noise

Scores: [ 6 6 5 5 ]

We present a novel perspective and algorithm for learning directed acyclic graphs (DAGs) from data generated by a linear structural equation model (SEM). First, we show that a linear SEM can be viewed as a linear transform that, in prior work, computes the data from a dense input vector of random valued root causes (as we will call them) associated with the nodes. Instead, we consider the case of (approximately) few root causes and also introduce noise in the measurement of the data. Intuitively, this means that the DAG data is produced by few data generating events whose effect percolates through the DAG. We prove identifiability in this new setting and show that the true DAG is the global minimizer of the \(L^0\)-norm of the vector of root causes. For data satisfying the few root causes assumption, we show superior performance compared to prior DAG learning methods.

POSTER-128: CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

Keywords: Time Series Forecasting;

Scores: [ 6 5 6 5 ]

Recently, multivariate time series (MTS) forecasting techniques have seen rapid development and widespread applications across various fields. Transformer-based and GNN-based methods have shown promising potential due to their strong ability to model interaction of time and variables. However, by conducting a comprehensive analysis of the real-world data, we observe that the temporal fluctuations and heterogeneity between variables are not well handled by existing methods. To address the above issues, we propose CrossGNN, a linear complexity GNN model to refine the cross-scale and cross-variable interaction for MTS. To deal with the unexpected noise in time dimension, an adaptive multi-scale identifier (AMSI) is leveraged to construct multi-scale time series with reduced noise. A Cross-Scale GNN is proposed to extract the scales with clearer trend and weaker noise. Cross-Variable GNN is proposed to utilize the homogeneity and heterogeneity between different variables. By simultaneously focusing on edges with higher saliency scores and constraining those edges with lower scores, the time and space complexity (i.e., \(O(L)\)) of CrossGNN can be linear with the input sequence length \(L\). Extensive experimental results on 8 real-world MTS datasets demonstrate the effectiveness of CrossGNN compared with state-of-the-art methods.

SPOTLIGHT-17: Proximity-Informed Calibration for Deep Neural Networks

Keywords: Calibration Uncertainty Estimation Trustworthiness Fairness Multicalibration

Scores: [ 6 7 7 6 ]

POSTER-129: RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing

Keywords: computer graphics rendering ray tracing GPU acceleration RL spatiotemporal latent space

Scores: [ 5 5 5 6 ]

Monte-Carlo path tracing is a powerful technique for realistic image synthesis but suffers from high levels of noise at low sample counts, limiting its use in real-time applications. To address this, we propose a framework with end-to-end training of a sampling importance network, a latent space encoder network, and a denoiser network. Our approach uses reinforcement learning to optimize the sampling importance network, thus avoiding explicit numerically approximated gradients. Our method does not aggregate the sampled values per pixel by averaging but keeps all sampled values which are then fed into the latent space encoder. The encoder replaces handcrafted spatiotemporal heuristics by learned representations in a latent space. Finally, a neural denoiser is trained to refine the output image. Our approach increases visual quality on several challenging datasets and reduces rendering times for equal quality by a factor of 1.6x compared to the previous state-of-the-art, making it a promising solution for real-time applications.

POSTER-130: Optimal Algorithms for the Inhomogeneous Spiked Wigner Model

Keywords: Spectral Method Community detection Wigner Spike model Random Matrix BBP transition Approximate Message Passing Spin glasses Statistical Physics

Scores: [ 6 5 7 6 ]

We study a spiked Wigner problem with an inhomogeneous noise profile. Our aim in this problem is to recover the signal passed through an inhomogeneous low-rank matrix channel. While the information-theoretic performances are well-known, we focus on the algorithmic problem. First, we derive an approximate message-passing algorithm (AMP) for the inhomogeneous problem and show that its rigorous state evolution coincides with the information-theoretic optimal Bayes fixed-point equations. Second, we deduce a simple and efficient spectral method that outperforms PCA and is shown to match the information-theoretic transition.

POSTER-131: Hierarchical Multi-Agent Skill Discovery

Keywords: Multi-Agent Reinforcement Learning Hierarchical Skill Discovery Probabilistic Graphical Model

Scores: [ 6 5 6 6 5 ]

Skill discovery has shown significant progress in unsupervised reinforcement learning. This approach enables the discovery of a wide range of skills without any extrinsic reward, which can be effectively combined to tackle complex tasks. However, such unsupervised skill learning has not been well applied to multi-agent reinforcement learning (MARL) due to two primary challenges. One is how to learn skills not only for the individual agents but also for the entire team, and the other is how to coordinate the skills of different agents to accomplish multi-agent tasks. To address these challenges, we present Hierarchical Multi-Agent Skill Discovery (HMASD), a two-level hierarchical algorithm for discovering both team and individual skills in MARL. The high-level policy employs a transformer structure to realize sequential skill assignment, while the low-level policy learns to discover valuable team and individual skills. We evaluate HMASD on sparse reward multi-agent benchmarks, and the results show that HMASD achieves significant performance improvements compared to strong MARL baselines.

POSTER-132: Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Keywords: language model distillation reasoning knowledge augmentation

Scores: [ 6 7 6 4 7 ]

Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be challenging due to their high computational requirements and concerns on data privacy.Previous studies have focused on building task-specific small Language Models (LMs) by fine-tuning them with labeled data or distilling LLMs. However, these approaches are ill-suited for knowledge-intensive reasoning tasks due to the limited capacity of small LMs in memorizing the knowledge required.Motivated by our theoretical analysis on memorization, we propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales obtained from LLMs with augmented knowledge retrieved from an external knowledge base. Moreover, we further propose a neural reranker to obtain documents relevant to rationale generation. We empirically show that KARD significantly improves the performance of small T5 and GPT models on the challenging knowledge-intensive reasoning datasets, namely MedQA-USMLE, StrategyQA, and OpenbookQA.Notably, our method makes the 250M T5 models achieve superior performance against the fine-tuned 3B models, having 12 times larger parameters, on both MedQA-USMLE and StrategyQA benchmarks.

POSTER-133: Robust Bayesian Satisficing

Keywords: robust satisficing regret minimization Gaussian processes

Scores: [ 6 6 5 6 ]

Distributional shifts pose a significant challenge to achieving robustness in contemporary machine learning. To overcome this challenge, robust satisficing (RS) seeks a robust solution to an unspecified distributional shift while achieving a utility above a desired threshold. This paper focuses on the problem of RS in contextual Bayesian optimization when there is a discrepancy between the true and reference distributions of the context. We propose a novel robust Bayesian satisficing algorithm called RoBOS for noisy black-box optimization. Our algorithm guarantees sublinear lenient regret under certain assumptions on the amount of distribution shift. In addition, we define a weaker notion of regret called robust satisficing regret, in which our algorithm achieves a sublinear upper bound independent of the amount of distribution shift. To demonstrate the effectiveness of our method, we apply it to various learning problems and compare it to other approaches, such as distributionally robust optimization.

POSTER-134: Towards Better Dynamic Graph Learning: New Architecture and Unified Library

Keywords: dynamic graph learning Transformer-based architecture dynamic graph library

Scores: [ 8 5 4 7 7 ]

POSTER-135: State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding

Keywords: Concept-Based Explanations Reinforcement Learning Human-AI Interaction

Scores: [ 4 7 7 6 ]

POSTER-136: Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning

Keywords: Spectral Clustering Incomplete Data Kernel Correction Self-expressive Affinity Learning

Scores: [ 5 7 7 5 ]

Spectral clustering has gained popularity for clustering non-convex data due to its simplicity and effectiveness. It is essential to construct a similarity graph using a high-quality affinity measure that models the local neighborhood relations among the data samples. However, incomplete data can lead to inaccurate affinity measures, resulting in degraded clustering performance. To address these issues, we propose an imputation-free framework with two novel approaches to improve spectral clustering on incomplete data. Firstly, we introduce a new kernel correction method that enhances the quality of the kernel matrix estimated on incomplete data with a theoretical guarantee, benefiting classical spectral clustering on pre-defined kernels. Secondly, we develop a series of affinity learning methods that equip the self-expressive framework with \(\ell_p\)-norm to construct an intrinsic affinity matrix with an adaptive extension. Our methods outperform existing data imputation and distance calibration techniques on benchmark datasets, offering a promising solution to spectral clustering on incomplete data in various real-world applications.

POSTER-137: Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards

Keywords: multi-armed bandits bounded rewards

Scores: [ 6 5 5 6 ]

We study \(K\)-armed bandit problems where the reward distributions of the arms are all supported on the \([0,1]\) interval. Maillard sampling\cite{maillard13apprentissage}, an attractive alternative to Thompson sampling, has recently been shown to achieve competitive regret guarantees in the sub-Gaussian reward setting\cite{bian2022maillard} while maintaining closed-form action probabilities, which is useful for offline policy evaluation. In this work, we analyze the Kullback-Leibler Maillard Sampling (KL-MS) algorithm, a natural extension of Maillard sampling {and a special case of Minimum Empirical Divergence (MED)~\cite{honda2011asymptotically}} for achieving a KL-style finite-time gap-dependent regret bound. We show that KL-MS enjoys the asymptotic optimality when the rewards are Bernoulli and has an {adaptive} worst-case regret bound of the form \(O(\sqrt{\mu^*(1-\mu^*) K T \ln K} + K \ln T)\), where \(\mu^*\) is the expected reward of the optimal arm, and \(T\) is the time horizon length; {this is the first time such adaptivity is reported in the literature for an algorithm with asymptotic optimality guarantees.}

POSTER-138: Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning

Keywords: chain-of-thought in-context learning attention compositional learning approximation length generalization

Scores: [ 6 7 5 5 ]

POSTER-139: LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

Keywords: medical imaging; self-supervised learning; graph matching; large-vision model

Scores: [ 7 8 8 6 6 ]

Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data. While pre-trained networks on ImageNet and vision-language foundation models trained on web-scale data are the prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images. To bridge this gap, we introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets, covering a large number of organs and modalities such as CT, MRI, X-ray, and Ultrasound. We benchmark several state-of-the-art self-supervised algorithms on this dataset and propose a novel self-supervised contrastive learning algorithm using a graph-matching formulation. The proposed approach makes three contributions: (i) it integrates prior pair-wise image similarity metrics based on local and global information; (ii) it captures the structural constraints of feature embeddings through a loss function constructed through a combinatorial graph-matching objective, and (iii) it can be trained efficiently end-to-end using modern gradient-estimation techniques for black-box solvers. We thoroughly evaluate the proposed LVM-Med on 15 downstream medical tasks ranging from segmentation and classification to object detection, and both for the in and out-of-distribution settings. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models. For challenging tasks such as Brain Tumor Classification or Diabetic Retinopathy Grading, LVM-Med improves previous vision-language models trained on 1 billion masks by 6-7% while using only a ResNet-50.

POSTER-140: Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs

Keywords: inverse optimal control probabilistic modeling motor control cognitive science

Scores: [ 5 6 7 5 6 7 4 5 ]

Inverse optimal control can be used to characterize behavior in sequential decision-making tasks. Most existing work, however, is limited to fully observable or linear systems, or requires the action signals to be known. Here, we introduce a probabilistic approach to inverse optimal control for partially observable stochastic non-linear systems with unobserved action signals, which unifies previous approaches to inverse optimal control with maximum causal entropy formulations. Using an explicit model of the noise characteristics of the sensory and motor systems of the agent in conjunction with local linearization techniques, we derive an approximate likelihood function for the model parameters, which can be computed within a single forward pass. We present quantitative evaluations on stochastic and partially observable versions of two classic control tasks and two human behavioral tasks. Importantly, we show that our method can disentangle perceptual factors and behavioral costs despite the fact that epistemic and pragmatic actions are intertwined in sequential decision-making under uncertainty, such as in active sensing and active learning. The proposed method has broad applicability, ranging from imitation learning to sensorimotor neuroscience.

POSTER-141: SODA: Robust Training of Test-Time Data Adaptors

Keywords: test-time data adaptation zeroth-order optimization out-of-distribution generalization

Scores: [ 6 5 5 5 ]

Adapting models deployed to test distributions can mitigate the performance degradation caused by distribution shifts. However, privacy concerns may render model parameters inaccessible. One promising approach involves utilizing zeroth-order optimization (ZOO) to train a data adaptor to adapt the test data to fit the deployed models. Nevertheless, the data adaptor trained with ZOO typically brings restricted improvements due to the potential corruption of data features caused by the data adaptor. To address this issue, we revisit ZOO in the context of test-time data adaptation. We find that the issue directly stems from the unreliable estimation of the gradients used to optimize the data adaptor, which is inherently due to the unreliable nature of the pseudo-labels assigned to the test data. Based on this observation, we propose pseudo-label-robust data adaptation (SODA) to improve the performance of data adaptation. Specifically, SODA leverages high-confidence predicted labels as reliable labels to optimize the data adaptor with ZOO for label prediction. For data with low-confidence predictions, SODA encourages the adaptor to preserve data information to mitigate data corruption. Empirical results indicate that SODA can significantly enhance the performance of deployed models in the presence of distribution shifts without requiring access to model parameters.

POSTER-142: Do Not Marginalize Mechanisms, Rather Consolidate!

Keywords: Structural Causal Models Marginalization Consolidation Compression

Scores: [ 7 6 6 ]

Structural causal models (SCMs) are a powerful tool for understanding the complex causal relationships that underlie many real-world systems. As these systems grow in size, the number of variables and complexity of interactions between them does, too. Thus, becoming convoluted and difficult to analyze. This is particularly true in the context of machine learning and artificial intelligence, where an ever increasing amount of data demands for new methods to simplify and compress large scale SCM. While methods for marginalizing and abstracting SCM already exist today, they may destroy the causality of the marginalized model. To alleviate this, we introduce the concept of consolidating causal mechanisms to transform large-scale SCM while preserving consistent interventional behaviour. We show consolidation is a powerful method for simplifying SCM, discuss reduction of computational complexity and give a perspective on generalizing abilities of consolidated SCM.

POSTER-143: Thrust: Adaptively Propels Large Language Models with External Knowledge

Keywords: knowledge-intensive natural language processing pre-trained language models instance-level adaptive knowledge usage

Scores: [ 6 5 4 7 ]

Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However, the existing information retrieval techniques could be costly and may even introduce noisy and sometimes misleading knowledge. To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary. To achieve this goal, we propose to model whether a PTLM contains enough knowledge to solve an instance with a novel metric, Thrust, which leverages the representation distribution of a small amount of seen instances. Extensive experiments demonstrate that Thrust is a good measurement of models' instance-level knowledgeability. Moreover, we can achieve higher cost-efficiency with the Thrust score as the retrieval indicator than the naive usage of external knowledge on 88% of the evaluated tasks with 26% average performance improvement. Such findings shed light on the real-world practice of knowledge-enhanced LMs with a limited budget for knowledge seeking due to computation latency or costs.

POSTER-144: Recasting Continual Learning as Sequence Modeling

Keywords: meta-continual learning sequence modeling Transformers efficient Transformers

Scores: [ 6 6 4 6 ]

In this work, we aim to establish a strong connection between two significant bodies of machine learning research: continual learning and sequence modeling.That is, we propose to formulate continual learning as a sequence modeling problem, allowing advanced sequence models to be utilized for continual learning.Under this formulation, the continual learning process becomes the forward pass of a sequence model.By adopting the meta-continual learning (MCL) framework, we can train the sequence model at the meta-level, on multiple continual learning episodes.As a specific example of our new formulation, we demonstrate the application of Transformers and their efficient variants as MCL methods.Our experiments on seven benchmarks, covering both classification and regression, show that sequence models can be an attractive solution for general MCL.

POSTER-145: Lending Interaction Wings to Recommender Systems with Conversational Agents

Keywords: Conversational Agent Recommender System Conversational Recommendation

Scores: [ 6 4 7 4 6 6 ]

An intelligent conversational agent (a.k.a., chat-bot) could embrace conversational technologies to obtain user preferences online, to overcome inherent limitations of recommender systems trained over the offline historical user behaviors. In this paper, we propose CORE, a new offline-training and online-checking framework to plug a COnversational agent into REcommender systems. Unlike most prior conversational recommendation approaches that systemically combine conversational and recommender parts through a reinforcement learning framework, CORE bridges the conversational agent and recommender system through a unified uncertainty minimization framework, which can be easily applied to any existing recommendation approach. Concretely, CORE treats a recommender system as an offline estimator to produce an estimated relevance score for each item, while CORE regards a conversational agent as an online checker that checks these estimated scores in each online session. We define uncertainty as the sum of unchecked relevance scores. In this regard, the conversational agent acts to minimize uncertainty via querying either attributes or items. Towards uncertainty minimization, we derive the certainty gain of querying each attribute and item, and develop a novel online decision tree algorithm to decide what to query at each turn. Our theoretical analysis reveals the bound of the expected number of turns of CORE in a cold-start setting. Experimental results demonstrate that CORE can be seamlessly employed on a variety of recommendation approaches, and can consistently bring significant improvements in both hot-start and cold-start settings.

POSTER-146: Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations

Keywords: partial differential equations physics turbulence stochastic differential equations physical simulation neural differential equations

Scores: [ 8 6 6 7 ]

We introduce a data-driven learning framework that assimilates two powerful ideas: ideal large eddy simulation (LES) from turbulence closure modeling and neural stochastic differential equations (SDE) for stochastic modeling. The ideal LES models the LES flow by treating each full-order trajectory as a random realization of the underlying dynamics, as such, the effect of small-scales is marginalized to obtain the deterministic evolution of the LES state. However, ideal LES is analytically intractable. In our work, we use a latent neural SDE to model the evolution of the stochastic process and an encoder-decoder pair for transforming between the latent space and the desired ideal flow field. This stands in sharp contrast to other types of neural parameterization of closure models where each trajectory is treated as a deterministic realization of the dynamics. We show the effectiveness of our approach (niLES – neural ideal LES) on two challenging chaotic dynamical systems: Kolmogorov flow at a Reynolds number of 20,000 and flow past a cylinder at Reynolds number 500. Compared to competing methods, our method can handle non-uniform geometries using unstructured meshes seamlessly. In particular, niLES leads to trajectories with more accurate statistics and enhances stability, particularly for long-horizon rollouts. (Source codes and datasets will be made publicly available.)

POSTER-147: FedNAR: Federated Optimization with Normalized Annealing Regularization

Keywords: Federated learning weight decay adaptive hyperparameters

Scores: [ 7 7 6 6 ]

Weight decay is a standard technique to improve generalization performance in modern deep neural network optimization, and is also widely adopted in federated learning (FL) to prevent overfitting in local clients. In this paper, we first explore the choices of weight decay and identify that weight decay value appreciably influences the convergence of existing FL algorithms. While preventing overfitting is crucial, weight decay can introduce a different optimization goal towards the global objective, which is further amplified in FL due to multiple local updates and heterogeneous data distribution.To address this challenge, we develop {\it Federated optimization with Normalized Annealing Regularization} (FedNAR), a simple yet effective and versatile algorithmic plug-in that can be seamlessly integrated into any existing FL algorithms. Essentially, we regulate the magnitude of each update by performing co-clipping of the gradient and weight decay.We provide a comprehensive theoretical analysis of FedNAR's convergence rate and conduct extensive experiments on both vision and language datasets with different backbone federated optimization algorithms. Our experimental results consistently demonstrate that incorporating FedNAR into existing FL algorithms leads to accelerated convergence and heightened model accuracy. Moreover, FedNAR exhibits resilience in the face of various hyperparameter configurations. Specifically, FedNAR has the ability to self-adjust the weight decay when the initial specification is not optimal, while the accuracy of traditional FL algorithms would markedly decline. Our codes are released at \href{}{}.

POSTER-148: Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context

Keywords: Time series forecasting multi-modal learning solar irradiance context-enriched learning

Scores: [ 6 7 6 7 ]

POSTER-149: Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

Keywords: distributed optimization convex optimization second-order similarity client sampling

Scores: [ 4 5 5 8 7 ]

SPOTLIGHT-18: Online Constrained Meta-Learning: Provable Guarantees for Generalization

Keywords: meta-learning; generalization

Scores: [ 6 8 7 6 ]

Meta-learning has attracted attention due to its strong ability to learn experiences from known tasks, which can speed up and enhance the learning process for new tasks. However, most existing meta-learning approaches only can learn from tasks without any constraint. This paper proposes an online constrained meta-learning framework, which continuously learns meta-knowledge from sequential learning tasks, and the learning tasks are subject to hard constraints. Beyond existing meta-learning analyses, we provide the upper bounds of optimality gaps and constraint violations produced by the proposed framework, which considers the dynamic regret of online learning, as well as the generalization ability of the task-specific models. Moreover, we provide a practical algorithm for the framework, and validate its superior effectiveness through experiments conducted on meta-imitation learning and few-shot image classification.

POSTER-150: Taming Local Effects in Graph-based Spatiotemporal Forecasting

Keywords: time series forecasting spatiotemporal forecasting graph-based spatiotemporal forecasting graph neural networks

Scores: [ 6 5 7 4 ]

Spatiotemporal graph neural networks have shown to be effective in time series forecasting applications, achieving better performance than standard univariate predictors in several settings. These architectures take advantage of a graph structure and relational inductive biases to learn a single (global) inductive model to predict any number of the input time series, each associated with a graph node. Despite the gain achieved in computational and data efficiency w.r.t. fitting a set of local models, relying on a single global model can be a limitation whenever some of the time series are generated by a different spatiotemporal stochastic process. The main objective of this paper is to understand the interplay between globality and locality in graph-based spatiotemporal forecasting, while contextually proposing a methodological framework to rationalize the practice of including trainable node embeddings in such architectures. We ascribe to trainable node embeddings the role of amortizing the learning of specialized components. Moreover, embeddings allow for 1) effectively combining the advantages of shared message-passing layers with node-specific parameters and 2) efficiently transferring the learned model to new node sets. Supported by strong empirical evidence, we provide insights and guidelines for specializing graph-based models to the dynamics of each time series and show how this aspect plays a crucial role in obtaining accurate predictions.

POSTER-151: FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation

Keywords: Data fusion heterogeneous treatment effects estimation shrinkage estimation tree-based method

Scores: [ 6 3 7 7 6 ]

This paper proposes a novel strategy for estimating the heterogeneous treatment effect called the Fused and Accurate Shrinkage Tree (\(\mathrm{FAST}\)). Our approach utilizes both trial and observational data to improve the accuracy and robustness of the estimator. Inspired by the concept of shrinkage estimation in statistics, we develop an optimal weighting scheme and a corresponding estimator that balances the unbiased estimator based on the trial data with the potentially biased estimator based on the observational data. Specifically, combined with tree-based techniques, we introduce a new split criterion that utilizes both trial data and observational data to more accurately estimate the treatment effect. Furthermore, we confirm the consistency of our proposed tree-based estimator and demonstrate the effectiveness of our criterion in reducing prediction error through theoretical analysis. The advantageous finite sample performance of the \(\mathrm{FAST}\) and its ensemble version over existing methods is demonstrated via simulations and real data analysis.

POSTER-152: Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking

Keywords: line-search gradient descent hypergradient adaptive methods smooth convex optimization preconditioning

Scores: [ 5 8 6 8 ]

The backtracking line-search is an effective technique to automatically tune the step-size in smooth optimization. It guarantees similar performance to using the theoretically optimal step-size. Many approaches have been developed to instead tune per-coordinate step-sizes, also known as diagonal preconditioners, but none of the existing methods are provably competitive with the optimal per-coordinate step-sizes. We propose multidimensional backtracking, an extension of the backtracking line-search to find good diagonal preconditioners for smooth convex problems. Our key insight is that the gradient with respect to the step-sizes, also known as hyper-gradients, yields separating hyperplanes that let us search for good preconditioners using cutting-plane methods. As black-box cutting-plane approaches like the ellipsoid method are computationally prohibitive, we develop an efficient algorithm tailored to our setting. Multidimensional backtracking is provably competitive with the best diagonal preconditioner and requires no manual tuning.

POSTER-153: Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

Keywords: robust reinforcement learning policy-based approach function approximation actor-critic

Scores: [ 5 7 6 6 ]

We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms mainly focus on the tabular setting under uncertainty sets that facilitate robust policy evaluation, but are no longer tractable when the number of states scales up. To this end, we propose two novel uncertainty set formulations, one based on double sampling and the other on an integral probability metric. Both make large-scale robust RL tractable even when one only has access to a simulator. We propose a robust natural actor-critic (RNAC) approach that incorporates the new uncertainty sets and employs function approximation. We provide finite-time convergence guarantees for the proposed RNAC algorithm to the optimal robust policy within the function approximation error. Finally, we demonstrate the robust performance of the policy learned by our proposed RNAC approach in multiple MuJoCo environments and a real-world TurtleBot navigation task.

POSTER-154: Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

Keywords: federated learning data heterogeneity partially class-disjoint data

Scores: [ 6 6 5 6 ]

Partially class-disjoint data (PCDD), a common yet under-explored data formation where each client contributes a part of classes (instead of all classes) of samples, severely challenges the performance of federated algorithms. Without full classes, the local objective will contradict the global objective, yielding the angle collapse problem for locally missing classes and the space waste problem for locally existing classes. As far as we know, none of the existing methods can intrinsically mitigate PCDD challenges to achieve holistic improvement in the bilateral views (both global view and local view) of federated learning. To address this dilemma, we are inspired by the strong generalization of simplex Equiangular Tight Frame (ETF) on the imbalanced data, and propose a novel approach called FedGELA where the classifier is globally fixed as a simplex ETF while locally adapted to the personal distributions. Globally, FedGELA provides fair and equal discrimination for all classes and avoids inaccurate updates of the classifier, while locally it utilizes the space of locally missing classes for locally existing classes. We conduct extensive experiments on a range of datasets to demonstrate that our FedGELA achieves promising performance (averaged improvement of 3.9% to FedAvg and 1.5% to best baselines) and provide both local and global convergence guarantees.

POSTER-155: Adapting Fairness Interventions to Missing Values

Keywords: algorithmic fairness discrimination missing values machine learning

Scores: [ 5 6 7 7 6 ]

Missing values in real-world data pose a significant and unique challenge to algorithmic fairness. Different demographic groups may be unequally affected by missing data, and the standard procedure for handling missing values where first data is imputed, then the imputed data is used for classification—a procedure referred to as "impute-then-classify"—can exacerbate discrimination. In this paper, we analyze how missing values affect algorithmic fairness. We first prove that training a classifier from imputed data can significantly worsen the achievable values of group fairness and average accuracy. This is because imputing data results in the loss of the missing pattern of the data, which often conveys information about the predictive label. We present scalable and adaptive algorithms for fair classification with missing values. These algorithms can be combined with any preexisting fairness-intervention algorithm to handle all possible missing patterns while preserving information encoded within the missing patterns. Numerical experiments with state-of-the-art fairness interventions demonstrate that our adaptive algorithms consistently achieve higher fairness and accuracy than impute-then-classify across different datasets.

POSTER-156: Subject-driven Text-to-Image Generation via Apprenticeship Learning

Keywords: Diffusion Model Image Generation Image Editing In-Context Learning

Scores: [ 6 7 6 6 5 ]

Recent text-to-image generation models like DreamBooth have made remarkable progress in generating highly customized images of a target subject, by fine-tuning an ``expert model'' for a given subject from a few examples.However, this process is expensive, since a new expert model must be learned for each subject. In this paper, we present SuTI, a Subject-driven Text-to-Image generator that replaces subject-specific fine tuning with {in-context} learning.Given a few demonstrations of a new subject, SuTI can instantly generate novel renditions of the subject in different scenes, without any subject-specific optimization.SuTI is powered by {apprenticeship learning}, where a single apprentice model is learned from data generated by a massive number of subject-specific expert models. Specifically, we mine millions of image clusters from the Internet, each centered around a specific visual subject. We adopt these clusters to train a massive number of expert models, each specializing in a different subject. The apprentice model SuTI then learns to imitate the behavior of these fine-tuned experts. SuTI can generate high-quality and customized subject-specific images 20x faster than optimization-based SoTA methods. On the challenging DreamBench and DreamBench-v2, our human evaluation shows that SuTI significantly outperforms existing models like InstructPix2Pix, Textual Inversion, Imagic, Prompt2Prompt, Re-Imagen and DreamBooth.

POSTER-157: Granger Components Analysis: Unsupervised learning of latent temporal dependencies

Keywords: components analysis unsupervised learning Granger Causality

Scores: [ 5 6 7 5 ]

A new technique for unsupervised learning of time series data based on the notion of Granger causality is presented. The technique learns pairs of projections of a multivariate data set such that the resulting components -- "driving" and "driven" -- maximize the strength of the Granger causality between the latent time series (how strongly the past of the driving signal predicts the present of the driven signal). A coordinate descent algorithm that learns pairs of coefficient vectors in an alternating fashion is developed and shown to blindly identify the underlying sources (up to scale) on simulated vector autoregressive (VAR) data. The technique is tested on scalp electroencephalography (EEG) data from a motor imagery experiment where the resulting components lateralize with the side of the cued hand, and also on functional magnetic resonance imaging (fMRI) data, where the recovered components express previously reported resting-state networks.

POSTER-158: ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion

Keywords: Gaussian process autoregression multi fidelity nonparametric Bayesian

Scores: [ 6 3 7 6 ]

POSTER-159: BayesDAG: Gradient-Based Posterior Inference for Causal Discovery

Keywords: Causal Discovery Structure Learning Bayesian Inference Variational Inference MCMC Generative Model

Scores: [ 5 6 7 5 ]

Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks. However, computational challenges arise due to joint inference over combinatorial space of Directed Acyclic Graphs (DAGs) and nonlinear functions. Despite recent progress towards efficient posterior inference over DAGs, existing methods are either limited to variational inference on node permutation matrices for linear causal models, leading to compromised inference accuracy, or continuous relaxation of adjacency matrices constrained by a DAG regularizer, which cannot ensure resulting graphs are DAGs. In this work, we introduce a scalable Bayesian causal discovery framework based on a combination of stochastic gradient Markov Chain Monte Carlo (SG-MCMC) and Variational Inference (VI) that overcomes these limitations. Our approach directly samples DAGs from the posterior without requiring any DAG regularization, simultaneously draws function parameter samples and is applicable to both linear and nonlinear causal models. To enable our approach, we derive a novel equivalence to the permutation-based DAG learning, which opens up possibilities of using any relaxed gradient estimator defined over permutations. To our knowledge, this is the first framework applying gradient-based MCMC sampling for causal discovery. Empirical evaluation on synthetic and real-world datasets demonstrate our approach's effectiveness compared to state-of-the-art baselines.

SPOTLIGHT-19: Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness

Keywords: Adversarial Average Precision Maximization Robust Average Precision Adversarial Ranking Robustness Adversarial Training

Scores: [ 5 8 6 6 7 ]

This paper seeks to address a gap in optimizing Average Precision (AP) while ensuring adversarial robustness, an area that has not been extensively explored to the best of our knowledge. AP maximization for deep learning has widespread applications, particularly when there is a significant imbalance between positive and negative examples. Although numerous studies have been conducted on adversarial training, they primarily focus on robustness concerning accuracy, ensuring that the average accuracy on adversarially perturbed examples is well maintained. However, this type of adversarial robustness is insufficient for many applications, as minor perturbations on a single example can significantly impact AP while not greatly influencing the accuracy of the prediction system. To tackle this issue, we introduce a novel formulation that combines an AP surrogate loss with a regularization term representing adversarial ranking robustness, which maintains the consistency between ranking of clean data and that of perturbed data. We then devise an efficient stochastic optimization algorithm to optimize the resulting objective. Our empirical studies, which compare our method to current leading adversarial training baselines and other robust AP maximization strategies, demonstrate the effectiveness of the proposed approach. Notably, our methods outperform a state-of-the-art method (TRADES) by more than 4% in terms of robust AP against PGD attacks while achieving 7% higher AP on clean data simultaneously on CIFAR10 and CIFAR100.The code is available at:

POSTER-160: VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

Keywords: backdoor diffusion model trustworthy

Scores: [ 5 6 5 5 ]

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image conditional generation. However, recent studies have shown that basic unconditional DMs (e.g., DDPM and DDIM) are vulnerable to backdoor injection, a type of output manipulation attack triggered by a maliciously embedded pattern at model input. This paper presents a unified backdoor attack framework (VillanDiffusion) to expand the current scope of backdoor analysis for DMs. Our framework covers mainstream unconditional and conditional DMs (denoising-based and score-based) and various training-free samplers for holistic evaluations. Experiments show that our unified framework facilitates the backdoor analysis of different DM configurations and provides new insights into caption-based backdoor attacks on DMs.

POSTER-161: Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Keywords: Visual relation detection Zero-short learning Scene graph generation

Scores: [ 5 5 5 5 6 ]

Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that identifies relationship (or interaction) types between object pairs within an image. However, naively utilizing CLIP with prevalent class-based prompts for zero-shot VRD has several weaknesses, e.g., it struggles to distinguish between different fine-grained relation types and it neglects essential spatial information of two objects. To this end, we propose a novel method for zero-shot VRD: RECODE, which solves RElation detection via COmposite DEscription prompts. Specifically, RECODE first decomposes each predicate category into subject, object, and spatial components. Then, it leverages large language models (LLMs) to generate description-based prompts (or visual cues) for each component. Different visual cues enhance the discriminability of similar relation categories from different perspectives, which significantly boosts performance in VRD. To dynamically fuse different cues, we further introduce a chain-of-thought method that prompts LLMs to generate reasonable weights for different visual cues. Extensive experiments on four VRD benchmarks have demonstrated the effectiveness and interpretability of RECODE.

SPOTLIGHT-20: Stein \(\Pi\)-Importance Sampling

Keywords: Bayesian discrepancy kernel sampling Stein's method

Scores: [ 7 6 6 7 6 ]

Stein discrepancies have emerged as a powerful tool for retrospective improvement of Markov chain Monte Carlo output. However, the question of how to design Markov chains that are well-suited to such post-processing has yet to be addressed. This paper studies Stein importance sampling, in which weights are assigned to the states visited by a \(\Pi\)-invariant Markov chain to obtain a consistent approximation of \(P\), the intended target. Surprisingly, the optimal choice of \(\Pi\) is not identical to the target \(P\); we therefore propose an explicit construction for \(\Pi\) based on a novel variational argument. Explicit conditions for convergence of Stein \(\Pi\)-Importance Sampling are established. For \(\approx 70\)% of tasks in the PosteriorDB benchmark, a significant improvement over the analogous post-processing of \(P\)-invariant Markov chains is reported.

POSTER-162: Outlier-Robust Wasserstein DRO

Keywords: distributionally robust optimization robust statistics optimal transport Wasserstein distance

Scores: [ 6 6 6 6 ]

Distributionally robust optimization (DRO) is an effective approach for data-driven decision-making in the presence of uncertainty. Geometric uncertainty due to~sampling or localized perturbations of data points is captured by Wasserstein DRO (WDRO), which seeks to learn a model that performs uniformly well over a Wasserstein ball centered around the observed data distribution. However, WDRO fails to account for non-geometric perturbations such as adversarial outliers, which can greatly distort the Wasserstein distance measurement and impede the learned model. We address this gap by proposing a novel outlier-robust WDRO framework for decision-making under both geometric (Wasserstein) perturbations and non-geometric (total variation (TV)) contamination that allows an \(\varepsilon\)-fraction of data to be arbitrarily corrupted. We design an uncertainty set using a certain robust Wasserstein ball that accounts for both perturbation types and derive minimax optimal excess risk bounds for this procedure that explicitly capture the Wasserstein and TV risks. We prove a strong duality result that enables tractable convex reformulations and efficient computation of our outlier-robust WDRO problem. When the loss function depends only on low-dimensional features of the data, we eliminate certain dimension dependencies from the risk bounds that are unavoidable in the general setting. Finally, we present experiments validating our theory on standard regression and classification tasks.

POSTER-163: Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards

Keywords: Normative Agency Design Reward Design Sequential Decision Making Reinforcement Learning Intertemporal Fairness Multi-Objective Decision Making

Scores: [ 6 6 6 ]

As the capabilities of artificial agents improve, they are being increasingly deployed to service multiple diverse objectives and stakeholders. However, the composition of these objectives is often performed ad hoc, with no clear justification. This paper takes a normative approach to multi-objective agency: from a set of intuitively appealing axioms, it is shown that Markovian aggregation of Markovian reward functions is not possible when the time preference (discount factor) for each objective may vary. It follows that optimal multi-objective agents must admit rewards that are non-Markovian with respect to the individual objectives. To this end, a practical non-Markovian aggregation scheme is proposed, which overcomes the impossibility with only one additional parameter for each objective. This work offers new insights into sequential, multi-objective agency and intertemporal choice, and has practical implications for the design of AI systems deployed to serve multiple generations of principals with varying time preference.

POSTER-164: Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms

Keywords: multi-armed bandit best of both worlds Follow-the-Regularized-Leader Tsallis entropy Shannon entropy Log-barrier

Scores: [ 6 7 6 6 ]

We study the problem of designing adaptive multi-armed bandit algorithms that perform optimally in both the stochastic setting and the adversarial setting simultaneously (often known as a best-of-both-world guarantee). A line of recent works shows that when configured and analyzed properly, the Follow-the-Regularized-Leader (FTRL) algorithm, originally designed for the adversarial setting, can in fact optimally adapt to the stochastic setting as well. Such results, however, critically rely on an assumption that there exists one unique optimal arm. Recently, Ito [2021] took the first step to remove such an undesirable uniqueness assumption for one particular FTRL algorithm withthe 1/2-Tsallis entropy regularizer. In this work, we significantly improve and generalize this result, showing that uniqueness is unnecessary for FTRL with a broad family of regularizers and a new learning rate schedule. For some regularizers, our regret bounds also improve upon prior results even when uniqueness holds. We further provide an application of our results to the decoupled exploration and exploitation problem, demonstrating that our techniques are broadly applicable.

SPOTLIGHT-21: High-dimensional Asymptotics of Denoising Autoencoders

Keywords: statistical physics replica method autoencoder exact asymptotics

Scores: [ 7 7 7 7 ]

We address the problem of denoising data from a Gaussian mixture using a two-layer non-linear autoencoder with tied weights and a skip connection. We consider the high-dimensional limit where the number of training samples and the input dimension jointly tend to infinity while the number of hidden units remains bounded. We provide closed-form expressions for the denoising mean-squared test error. Building on this result, we quantitatively characterize the advantage of the considered architecture over the autoencoder without the skip connection that relates closely to principal component analysis. We further show that our results capture accurately the learning curves on a range of real datasets.

SPOTLIGHT-22: Provable benefits of score matching

Keywords: theory score matching exponential families sample complexity computational hardness

Scores: [ 7 7 6 7 ]

POSTER-165: Collaboratively Learning Linear Models with Structured Missing Data

Keywords: Collaborative Learning Missing Data Sensors Linear Regression

Scores: [ 5 6 4 5 7 ]

We study the problem of collaboratively learning least squares estimates for \(m\) agents. Each agent observes a different subset of the features---e.g., containing data collected from sensors of varying resolution. Our goal is to determine how to coordinate the agents in order to produce the best estimator for each agent. We propose a distributed, semi-supervised algorithm Collab, consisting of three steps: local training, aggregation, and distribution. Our procedure does not require communicating the labeled data, making it communication efficient and useful in settings where the labeled data is inaccessible. Despite this handicap, our procedure is nearly asymptotically, local-minimax optimal---even among estimators allowed to communicate the labeled data such as imputation methods. We test our method on US Census data. We also discuss generalizations of our method to non-Gaussian feature settings, non-linear settings, and Federated Learning.

POSTER-166: Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

Keywords: Graph-based Semi-supervised Learning Affinity Graph Construction

Scores: [ 7 6 6 4 7 ]

Graph-based semi-supervised learning (GSSL) serves as a powerful tool to model the underlying manifold structures of samples in high-dimensional spaces. It involves two phases: constructing an affinity graph from available data and inferring labels for unlabeled nodes on this graph. While numerous algorithms have been developed for label inference, the crucial graph construction phase has received comparatively less attention, despite its significant influence on the subsequent phase. In this paper, we present an optimal asymmetric graph structure for the label inference phase with theoretical motivations. Unlike existing graph construction methods, we differentiate the distinct roles that labeled nodes and unlabeled nodes could play. Accordingly, we design an efficient block-wise graph learning algorithm with a global convergence guarantee. Other benefits induced by our method, such as enhanced robustness to noisy node features, are explored as well. Finally, we perform extensive experiments on synthetic and real-world datasets to demonstrate its superiority to the state-of-the-art graph construction methods in GSSL.

POSTER-167: Language-driven Scene Synthesis using Multi-conditional Diffusion Model

Keywords: scene synthesis language-driven diffusion models multi-conditional generation 3D point cloud

Scores: [ 6 7 4 5 6 ]

Scene synthesis is a challenging problem with several industrial applications. Recently, substantial efforts have been directed to synthesize the scene using human motions, room layouts, or spatial graphs as the input. However, few studies have addressed this problem from multiple modalities, especially combining text prompts. In this paper, we propose a language-driven scene synthesis task, which is a new task that integrates text prompts, human motion, and existing objects for scene synthesis. Unlike other single-condition synthesis tasks, our problem involves multiple conditions and requires a strategy for processing and encoding them into a unified space. To address the challenge, we present a multi-conditional diffusion model, which differs from the implicit unification approach of other diffusion literature by explicitly predicting the guiding points for the original data distribution. We demonstrate that our approach is theoretically supportive. The intensive experiment results illustrate that our method outperforms state-of-the-art benchmarks and enables natural scene editing applications. The source code and dataset can be accessed at

POSTER-168: What can a Single Attention Layer Learn? A Study Through the Random Features Lens

Keywords: transformers attention deep learning theory random features

Scores: [ 5 7 5 5 ]

Attention layers---which map a sequence of inputs to a sequence of outputs---are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a rigorous theoretical study on the learning and generalization of a single multi-head attention layer, with a sequence of key vectors and a separate query vector as input. We consider the random feature setting where the attention layer has a large number of heads, with randomly sampled frozen query and key matrices, and trainable value matrices. We show that such a random-feature attention layer can express a broad class of target functions that are permutation invariant to the key vectors. We further provide quantitative excess risk bounds for learning these target functions from finite samples, using random feature attention with finitely many heads.Our results feature several implications unique to the attention structure compared with existing random features theory for neural networks, such as (1) Advantages in the sample complexity over standard two-layer random-feature networks; (2) Concrete and natural classes of functions that can be learned efficiently by a random-feature attention layer; and (3) The effect of the sampling distribution of the query-key weight matrix (the product of the query and key matrix), where Gaussian random weights with a non-zero mean result in better sample complexities over the zero-mean counterpart for learning certain natural target functions. Experiments on simulated data corroborate our theoretical findings and further illustrate the interplay between the sample size and the complexity of the target function.

POSTER-169: Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

Keywords: Interpretability Robustness Fine-Grained Representation Learning Graph Theory Information Theory

Scores: [ 6 5 7 ]

Recent advances in fine-grained representation learning leverage local-to-global (emergent) relationships for achieving state-of-the-art results. The relational representations relied upon by such methods, however, are abstract. We aim to deconstruct this abstraction by expressing them as interpretable graphs over image views. We begin by theoretically showing that abstract relational representations are nothing but a way of recovering transitive relationships among local views. Based on this, we design Transitivity Recovering Decompositions (TRD), a graph-space search algorithm that identifies interpretable equivalents of abstract emergent relationships at both instance and class levels, and with no post-hoc computations. We additionally show that TRD is provably robust to noisy views, with empirical evidence also supporting this finding. The latter allows TRD to perform at par or even better than the state-of-the-art, while being fully interpretable. Implementation is available at

POSTER-170: Improving Diffusion-Based Image Synthesis with Context Prediction

Keywords: Diffusion Model Image Generation

Scores: [ 6 6 5 6 6 ]

Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a pixel-wise or feature-wise constraint along spatial axes. However, such point-based reconstruction may fail to make each predicted pixel/feature fully preserve its neighborhood context, impairing diffusion-based image synthesis. As a powerful source of automatic supervisory signal, context has been well studied for learning representations. Inspired by this, we for the first time propose ConPreDiff to improve diffusion-based image synthesis with context prediction. We explicitly reinforce each point to predict its neighborhood context (i.e., multi-stride pixels/features) with a context decoder at the end of diffusion denoising blocks in training stage, and remove the decoder for inference. In this way, each point can better reconstruct itself by preserving its semantic connections with neighborhood context. This new paradigm of ConPreDiff can generalize to arbitrary discrete and continuous diffusion backbones without introducing extra parameters in sampling procedure. Extensive experiments are conducted on unconditional image generation, text-to-image generation and image inpainting tasks. Our ConPreDiff consistently outperforms previous methods and achieves new SOTA text-to-image generation results on MS-COCO, with a zero-shot FID score of 6.21.

SPOTLIGHT-23: Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications

Keywords: Criticality Gaussian Process Jacobian LayerNorm Residual connections ResNet

Scores: [ 6 7 6 7 ]

Deep neural networks are notorious for defying theoretical treatment. However, when the number of parameters in each layer tends to infinity, the network function is a Gaussian process (GP) and quantitatively predictive description is possible. Gaussian approximation allows one to formulate criteria for selecting hyperparameters, such as variances of weights and biases, as well as the learning rate. These criteria rely on the notion of criticality defined for deep neural networks. In this work we describe a new practical way to diagnose criticality. We introduce partial Jacobians of a network, defined as derivatives of preactivations in layer \(l\) with respect to preactivations in layer \(l_0\leq l\). We derive recurrence relations for the norms of partial Jacobians and utilize these relations to analyze criticality of deep fully connected neural networks with LayerNorm and/or residual connections. We derive and implement a simple and cheap numerical test that allows one to select optimal initialization for a broad class of deep neural networks; containing fully connected, convolutional and normalization layers. Using these tools we show quantitatively that proper stacking of the LayerNorm (applied to preactivations) and residual connections leads to an architecture that is critical for any initialization. Finally, we apply our methods to analyze ResNet and MLP-Mixer architectures; demonstrating the everywhere-critical regime.

POSTER-171: Small batch deep reinforcement learning

Keywords: Reinforcement Learning Deep Reinforcement Learning Value based Batch Size

Scores: [ 7 7 7 4 ]

In value-based deep reinforcement learning with replay memories, the batch size parameter specifies how many transitions to sample for each gradient update. Although critical to the learning process, this value is typically not adjusted when proposing new algorithms. In this work we present a broad empirical study that suggests reducing the batch size can result in a number of significant performance gains; this is surprising, as the general tendency when training neural networks is towards larger batch sizes for improved performance. We complement our experimental findings with a set of empirical analyses towards better understanding this phenomenon.

POSTER-172: Progressive Ensemble Distillation: Building Ensembles for Efficient Inference

Keywords: Edge computing compression efficient inference distillation and inference run-time tradeoff inference-time tradeoff on-device user-side client-side

Scores: [ 6 6 5 5 6 ]

Knowledge distillation is commonly used to compress an ensemble of models into a single model. In this work we study the problem of progressive ensemble distillation: Given a large, pretrained teacher model , we seek to decompose the model into an ensemble of smaller, low-inference cost student models . The resulting ensemble allows for flexibly tuning accuracy vs. inference cost, which can be useful for a multitude of applications in efficient inference. Our method, B-DISTIL, uses a boosting procedure that allows function composition based aggregation rules to construct expressive ensembles with similar performance as using much smaller student models. We demonstrate the effectiveness of B-DISTIL by decomposing pretrained models across a variety of image, speech, and sensor datasets. Our method comes with strong theoretical guarantees in terms of convergence as well as generalization.

POSTER-173: Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis

Keywords: diffusion models post-training quantization

Scores: [ 6 5 5 5 4 ]

While diffusion models have demonstrated exceptional image generation capabilities, the iterative noise estimation process required for these models is compute-intensive and their practical implementation is limited by slow sampling speeds. In this paper, we propose a novel approach to speed up the noise estimation network by leveraging the robustness of early-stage diffusion models. Our findings indicate that inaccurate computation during the early-stage of the reverse diffusion process has minimal impact on the quality of generated images, as this stage primarily outlines the image while later stages handle the finer details that require more sensitive information. To improve computational efficiency, we combine our findings with post-training quantization (PTQ) to introduce a method that utilizes low-bit activation for the early reverse diffusion process while maintaining high-bit activation for the later stages. Experimental results show that the proposed method can accelerate the early-stage computation without sacrificing the quality of the generated images.

POSTER-174: A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)

Keywords: CLIP

Scores: [ 6 4 5 7 6 ]

POSTER-175: Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability

Keywords: simulation-based inference inverse problem bayesian inference uncertainty quantification generative modeling

Scores: [ 6 7 7 7 ]

Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence. Predominantly, the likelihood function is only implicitly established by a simulator posing the need for simulation-based inference (SBI). However, the existing algorithms can yield overconfident posteriors (Hermans et al., 2022) defeating the whole purpose of credibility if the uncertainty quantification is inaccurate. We propose to include a calibration term directly into the training objective of the neural model in selected amortized SBI techniques. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. The proposed method is not tied to any particular neural model and brings moderate computational overhead compared to the profits it introduces. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference. We empirically show on six benchmark problems that the proposed method achieves competitive or better results in terms of coverage and expected posterior density than the previously existing approaches.

POSTER-176: An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint

Keywords: approximate nearest neighbor search attribute filtering high-dimensional vector proximity graph

Scores: [ 8 7 6 4 ]

This paper introduces an efficient and robust framework for hybrid query (HQ) processing, which combines approximate nearest neighbor search (ANNS) with attribute constraint. HQ aims to find objects that are similar to a feature vector and match some structured attributes. Existing methods handle ANNS and attribute filtering separately, leading to inefficiency and inaccuracy. Our framework, called native hybrid query (NHQ), builds a composite index based on proximity graph (PG) and applies joint pruning for HQ. We can easily adapt existing PGs to this framework for efficient HQ processing. We also propose two new navigable PGs (NPGs) with optimized edge selection and routing, which improve the overall ANNS performance. We implement five HQ methods based on the proposed NPGs and existing PGs in NHQ, and show that they outperform the state-of-the-art methods on 10 real-world datasets (up to 315$\times$ faster with the same accuracy).

POSTER-177: Learning a 1-layer conditional generative model in total variation

Keywords: Generative models distribution learning maximum likelihood estimation

Scores: [ 7 7 3 6 5 ]

A conditional generative model is a method for sampling from a conditional distribution \(p(y \mid x)\). For example, one may want to sample an image of a cat given the label ``cat''. A feed-forward conditional generative model is a function \(g(x, z)\) that takes the input \(x\) and a random seed \(z\), and outputs a sample \(y\) from \(p(y \mid x)\). Ideally the distribution of outputs \((x, g(x, z))\) would be close in total variation to the ideal distribution \((x, y)\).Generalization bounds for other learning models require assumptions on the distribution of \(x\), even in simple settings like linear regression with Gaussian noise. We show these assumptions are unnecessary in our model, for both linear regression and single-layer ReLU networks. Given samples \((x, y)\), we show how to learn a 1-layer ReLU conditional generative model in total variation. As our result has no assumption on the distribution of inputs \(x\), if we are given access to the internal activations of a deep generative model, we can compose our 1-layer guarantee to progressively learn the deep model using a near-linear number of samples.

ORAL-3: A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization

Keywords: Constrained Minimax Optimization; nonconvex- nonconcave

Scores: [ 9 9 6 8 ]

In this paper, we propose a novel extra-gradient difference acceleration algorithm for solving constrained nonconvex-nonconcave (NC-NC) minimax problems. In particular, we design a new extra-gradient difference step to obtain an important quasi-cocoercivity property, which plays a key role to significantly improve the convergence rate in the constrained NC-NC setting without additional structural assumption. Then momentum acceleration is also introduced into our dual accelerating update step. Moreover, we prove that, to find an \(\epsilon\)-stationary point of the function \(f\), our algorithm attains the complexity \(\mathcal{O}(\epsilon^{-2})\) in the constrained NC-NC setting, while the best-known complexity bound is \(\widetilde{\mathcal{O}}(\epsilon^{-4})\), where \(\widetilde{\mathcal{O}}(\cdot)\) hides logarithmic factors compared to \(\mathcal{O}(\cdot)\). As the special cases of the constrained NC-NC setting, our algorithm can also obtain the same complexity \(\mathcal{O}(\epsilon^{-2})\) for both the nonconvex-concave (NC-C) and convex-nonconcave (C-NC) cases, while the best-known complexity bounds are \(\widetilde{\mathcal{O}}(\epsilon^{-2.5})\) for the NC-C case and \(\widetilde{\mathcal{O}}(\epsilon^{-4})\) for the C-NC case. For fair comparison with existing algorithms, we also analyze the complexity bound to find \(\epsilon\)-stationary point of the primal function \(\phi\) for the constrained NC-C problem, which shows that our algorithm can improve the complexity bound from \(\widetilde{\mathcal{O}}(\epsilon^{-3})\) to \(\mathcal{O}(\epsilon^{-2})\). To the best of our knowledge, this is the first time that the proposed algorithm improves the best-known complexity bounds from \(\mathcal{O}(\epsilon^{-4})\) and \(\widetilde{\mathcal{O}}(\epsilon^{-3})\) to \(\mathcal{O}(\epsilon^{-2})\) in both the NC-NC and NC-C settings.

POSTER-178: Online Corrupted User Detection and Regret Minimization

Keywords: online learning online corrupted user detection clustering of bandits

Scores: [ 5 7 6 7 ]

In real-world online web systems, multiple users usually arrive sequentially into the system. For applications like click fraud and fake reviews, some users can maliciously perform corrupted (disrupted) behaviors to trick the system. Therefore, it is crucial to design efficient online learning algorithms to robustly learn from potentially corrupted user behaviors and accurately identify the corrupted users in an online manner. Existing works propose bandit algorithms robust to adversarial corruption. However, these algorithms are designed for a single user, and cannot leverage the implicit social relations among multiple users for more efficient learning. Moreover, none of them consider how to detect corrupted users online in the multiple-user scenario. In this paper, we present an important online learning problem named LOCUD to learn and utilize unknown user relations from disrupted behaviors to speed up learning, and identify the corrupted users in an online setting. To robustly learn and utilize the unknown relations among potentially corrupted users, we propose a novel bandit algorithm RCLUB-WCU. To detect the corrupted users, we devise a novel online detection algorithm OCCUD based on RCLUB-WCU's inferred user relations. We prove a regret upper bound for RCLUB-WCU, which asymptotically matches the lower bound with respect to \(T\) up to logarithmic factors, and matches the state-of-the-art results in degenerate cases. We also give a theoretical guarantee for the detection accuracy of OCCUD. With extensive experiments, our methods achieve superior performance over previous bandit algorithms and high corrupted user detection accuracy.

POSTER-179: Restart Sampling for Improving Generative Processes

Keywords: Generative models diffusion models PFGM sampling

Scores: [ 5 6 7 5 6 ]

Generative processes that involve solving differential equations, such as diffusion models, frequently necessitate balancing speed and quality. ODE-based samplers are fast but plateau in performance while SDE-based samplers deliver higher sample quality at the cost of increased sampling time. We attribute this difference to sampling errors: ODE-samplers involve smaller discretization errors while stochasticity in SDE contracts accumulated errors. Based on these findings, we propose a novel sampling algorithm called \textit{Restart} in order to better balance discretization errors and contraction. The sampling method alternates between adding substantial noise in additional forward steps and strictly following a backward ODE. Empirically, Restart sampler surpasses previous SDE and ODE samplers in both speed and accuracy. Restart not only outperforms the previous best SDE results, but also accelerates the sampling speed by 10-fold / 2-fold on CIFAR-10 / ImageNet \(64{\times} 64\). In addition, it attains significantly better sample quality than ODE samplers within comparable sampling times. Moreover, Restart better balances text-image alignment/visual quality versus diversity than previous samplers in the large-scale text-to-image Stable Diffusion model pre-trained on LAION \(512{\times} 512\). Code is available at

POSTER-180: Sharp Calibrated Gaussian Processes

Keywords: Gaussian Processes Frequentist Statistics Kernel Methods Model Selection and Structure Learning Regression

Scores: [ 5 6 6 7 ]

While Gaussian processes are a mainstay for various engineering and scientific applications, the uncertainty estimates don't satisfy frequentist guarantees and can be miscalibrated in practice. State-of-the-art approaches for designing calibrated models rely on inflating the Gaussian process posterior variance, which yields confidence intervals that are potentially too coarse. To remedy this, we present a calibration approach that generates predictive quantiles using a computation inspired by the vanilla Gaussian process posterior variance but using a different set of hyperparameters chosen to satisfy an empirical calibration constraint. This results in a calibration approach that is considerably more flexible than existing approaches, which we optimize to yield tight predictive quantiles. Our approach is shown to yield a calibrated model under reasonable assumptions. Furthermore, it outperforms existing approaches in sharpness when employed for calibrated regression.

POSTER-181: Improving Self-supervised Molecular Representation Learning using Persistent Homology

Keywords: Graph Neural Networks Molecular Representation Learning Persistent Homology Contrastive Learning Self-supervised Learning

Scores: [ 7 6 3 5 7 ]

Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets. The importance of the topic is reflected in the variety of paradigms and architectures that have been investigated recently, most focus on designing views for contrastive learning.In this paper, we study SSL based on persistent homology (PH), a mathematical tool for modeling topological features of data that persist across multiple scales. It has several unique features which particularly suit SSL, naturally offering: different views of the data, stability in terms of distance preservation, and the opportunity to flexibly incorporate domain knowledge.We (1) investigate an autoencoder, which shows the general representational power of PH, and (2) propose a contrastive loss that complements existing approaches. We rigorously evaluate our approach for molecular property prediction and demonstrate its particular features in improving the embedding space:after SSL, the representations are better and offer considerably more predictive power than the baselines over different probing tasks; our loss increases baseline performance, sometimes largely; and we often obtain substantial improvements over very small datasets, a common scenario in practice.

POSTER-182: Ambient Diffusion: Learning Clean Distributions from Corrupted Data

Keywords: corrupted data generative models ambient gan inverse problems learning from measurements

Scores: [ 6 7 6 6 ]

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to acquire. Another benefit of our approach is the ability to train generative models that are less likely to memorize any individual training sample, since they never observe clean training data. Our main idea is to introduce additional measurement distortion during the diffusion process and require the model to predict the original corrupted image from the further corrupted image. We prove that our method leads to models that learn the conditional expectation of the full uncorrupted image given this additional measurement corruption. This holds for any corruption process that satisfies some technical conditions (and in particular includes inpainting and compressed sensing). We train models on standard benchmarks (CelebA, CIFAR-10 and AFHQ) and show that we can learn the distribution even when all the training samples have 90% of their pixels missing. We also show that we can finetune foundation models on small corrupted datasets (e.g. MRI scans with block corruptions) and learn the clean distribution without memorizing the training set.

POSTER-183: Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

Keywords: Reinforcement learning sparse reward return decomposition causal modeling

Scores: [ 5 5 4 7 5 ]

A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step from observed sequences. While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contributions of state and action from a causal perspective, resulting in an interpretable reward redistribution and preserving policy invariance. In this paper, we start by studying the role of causal generative models in reward redistribution by characterizing the generation of Markovian rewards and trajectory-wise long-term return and further propose a framework, called Generative Return Decomposition (GRD), for policy optimization in delayed reward scenarios. Specifically, GRD first identifies the unobservable Markovian rewards and causal relations in the generative process. Then, GRD makes use of the identified causal generative model to form a compact representation to train policy over the most favorable subspace of the state space of the agent. Theoretically, we show that the unobservable Markovian reward function is identifiable, as well as the underlying causal structure and causal models. Experimental results show that our method outperforms state-of-the-art methods and the provided visualization further demonstrates the interpretability of our method.The project page is located at

POSTER-184: InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion

Keywords: Contrastive learning; Point cloud completion

Scores: [ 6 5 9 5 5 ]

POSTER-185: Compositional Sculpting of Iterative Generative Processes

Keywords: generative model composition GFlowNets diffusion models classifier guidance probabilistic methods

Scores: [ 6 6 6 7 7 6 ]

High training costs of generative models and the need to fine-tune them for specific tasks have created a strong interest in model reuse and composition.A key challenge in composing iterative generative processes, such as GFlowNets and diffusion models, is that to realize the desired target distribution, all steps of the generative process need to be coordinated, and satisfy delicate balance conditions.In this work, we propose Compositional Sculpting: a general approach for defining compositions of iterative generative processes. We then introduce a method for sampling from these compositions built on classifier guidance.We showcase ways to accomplish compositional sculpting in both GFlowNets and diffusion models. We highlight two binary operations \(\\unicode{x2014}\) the \(\\textit{harmonic mean}\\unicode{x00A0}(p_1 \\otimes p_2\)) and the \(\\textit{contrast}\\unicode{x00A0}(p_1 \\,\\unicode{x25D1}\\,\\, p_2\)) between pairs, and the generalization of these operations to multiple component distributions.We offer empirical results on image and molecular generation tasks. Project codebase:

POSTER-186: Hyper-HMM: aligning human brains and semantic features in a common latent event space

Keywords: Brain Imaging Other Cognitive Science Other Neuroscience

Scores: [ 4 4 6 6 8 ]

Naturalistic stimuli evoke complex neural responses with spatial and temporal properties that differ across individuals. Current alignment methods focus on either spatial hyperalignment (assuming exact temporal correspondence) or temporal alignment (assuming exact spatial correspondence). Here, we propose a hybrid model, the Hyper-HMM, that simultaneously aligns both temporal and spatial features across brains. The model learns to linearly project voxels to a reduced-dimension latent space, in which timecourses are segmented into corresponding temporal events. This approach allows tracking of each individual's mental trajectory through an event sequence, and also allows for alignment with other feature spaces such as stimulus content. Using an fMRI dataset in which students watch videos of class lectures, we demonstrate that the Hyper-HMM can be used to map all participants and the semantic content of the videos into a common low-dimensional space, and that these mappings generalize to held-out data. Our model provides a new window into individual cognitive dynamics evoked by complex naturalistic stimuli.

POSTER-187: Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

Keywords: Mixture Model Minimax Rate Maximum Likelihood Estimation

Scores: [ 6 7 6 6 3 ]

We study the maximum likelihood estimation (MLE) in the multivariate deviated model where the data are generated from the density function \((1-\lambda^{\ast})h_{0}(x)+\lambda^{\ast}f(x|\mu^{\ast}, \Sigma^{\ast})\) in which \(h_{0}\) is a known function, \(\lambda^{\ast} \in [0,1]\) and \((\mu^{\ast}, \Sigma^{\ast})\) are unknown parameters to estimate. The main challenges in deriving the convergence rate of the MLE mainly come from two issues: (1) The interaction between the function \(h_{0}\) and the density function \(f\); (2) The deviated proportion \(\lambda^{\ast}\) can go to the extreme points of \([0,1]\) as the sample size tends to infinity. To address these challenges, we develop the \emph{distinguishability condition} to capture the linear independent relation between the function \(h_{0}\) and the density function \(f\). We then provide comprehensive convergence rates of the MLE via the vanishing rate of \(\lambda^{\ast}\) to zero as well as the distinguishability of two functions \(h_{0}\) and \(f\).

POSTER-188: Balanced Training for Sparse GANs

Keywords: Dynamics sparse training; pruning; neural network pruning; empirical deep learning

Scores: [ 5 4 8 5 ]

Over the past few years, there has been growing interest in developing larger and deeper neural networks, including deep generative models like generative adversarial networks (GANs). However, GANs typically come with high computational complexity, leading researchers to explore methods for reducing the training and inference costs. One such approach gaining popularity in supervised learning is dynamic sparse training (DST), which maintains good performance while enjoying excellent training efficiency. Despite its potential benefits, applying DST to GANs presents challenges due to the adversarial nature of the training process. In this paper, we propose a novel metric called the balance ratio (BR) to study the balance between the sparse generator and discriminator. We also introduce a new method called balanced dynamic sparse training (ADAPT), which seeks to control the BR during GAN training to achieve a good trade-off between performance and computational cost. Our proposed method shows promising results on multiple datasets, demonstrating its effectiveness.

ORAL-4: Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Keywords: Learning Theory Regression PAC Learning Online Learning

Scores: [ 8 9 6 7 8 ]

ORAL-5: Visual Instruction Tuning

Keywords: visual instruction tuning instruction tuning multimodal LLM GPT

Scores: [ 6 8 8 5 ]

Instruction tuning large language models (LLMs) using machine-generated instruction-following data has been shown to improve zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. We present the first attempt to use language-only GPT-4 to generate multimodal language-image instruction-following data. By instruction tuning on such generated data, we introduce LLaVA: Large Language and Vision Assistant, an end-to-end trained large multimodal model that connects a vision encoder and an LLM for general-purpose visual and language understanding. To facilitate future research on visual instruction following, we construct two evaluation benchmarks with diverse and challenging application-oriented tasks. Our experiments show that LLaVA demonstrates impressive multimodal chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make GPT-4 generated visual instruction tuning data, our model, and code publicly available.

POSTER-189: GAUCHE: A Library for Gaussian Processes in Chemistry

Keywords: Gaussian processes Bayesian optimization Chemistry Molecular Machine Learning Applications Software

Scores: [ 6 5 7 3 8 ]

We introduce GAUCHE, an open-source library for GAUssian processes in CHEmistry. Gaussian processes have long been a cornerstone of probabilistic machine learning, affording particular advantages for uncertainty quantification and Bayesian optimisation. Extending Gaussian processes to molecular representations, however, necessitates kernels defined over structured inputs such as graphs, strings and bit vectors. By providing such kernels in a modular, robust and easy-to-use framework, we seek to enable expert chemists and materials scientists to make use of state-of-the-art black-box optimization techniques. Motivated by scenarios frequently encountered in practice, we showcase applications for GAUCHE in molecular discovery, chemical reaction optimisation and protein design. The codebase is made available at

SPOTLIGHT-24: Adaptive whitening with fast gain modulation and slow synaptic plasticity

Keywords: neuroscience adaptation whitening efficient coding recurrent neural network gain modulation synaptic plasticity local learning rules

Scores: [ 6 7 7 7 ]

Neurons in early sensory areas rapidly adapt to changing sensory statistics, both by normalizing the variance of their individual responses and by reducing correlations between their responses. Together, these transformations may be viewed as an adaptive form of statistical whitening. Existing mechanistic models of adaptive whitening exclusively use either synaptic plasticity or gain modulation as the biological substrate for adaptation; however, on their own, each of these models has significant limitations. In this work, we unify these approaches in a normative multi-timescale mechanistic model that adaptively whitens its responses with complementary computational roles for synaptic plasticity and gain modulation. Gains are modified on a fast timescale to adapt to the current statistical context, whereas synapses are modified on a slow timescale to match structural properties of the input statistics that are invariant across contexts. Our model is derived from a novel multi-timescale whitening objective that factorizes the inverse whitening matrix into basis vectors, which correspond to synaptic weights, and a diagonal matrix, which corresponds to neuronal gains. We test our model on synthetic and natural datasets and find that the synapses learn optimal configurations over long timescales that enable adaptive whitening on short timescales using gain modulation.

POSTER-190: Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Keywords: Long-tail object detection visual semantics soft supervision

Scores: [ 5 7 6 5 ]

POSTER-191: Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework

Keywords: Bayesian bandits approximate Bayesian inference Bayesian Upper Confidence Bound optimal regret order bounded inference error

Scores: [ 7 6 5 ]

Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. However, there is a large discrepancy between the superior practical performance of these approaches and their theoretical justification. Previous research only indicates a negative theoretical result: Thompson sampling could have a worst-case linear regret \(\Omega(T)\) with a constant threshold on the inference error measured by one \(\alpha\)-divergence. To bridge this gap, we propose an Enhanced Bayesian Upper Confidence Bound (EBUCB) framework that can efficiently accommodate bandit problems in the presence of approximate inference. Our theoretical analysis demonstrates that for Bernoulli multi-armed bandits, EBUCB can achieve the optimal regret order \(O(\log T)\) if the inference error measured by two different \(\alpha\)-divergences is less than a constant, regardless of how large this constant is. To our best knowledge, our study provides the first theoretical regret bound that is better than \(o(T)\) in the setting of constant approximate inference error. Furthermore, in concordance with the negative results in previous studies, we show that only one bounded \(\alpha\)-divergence is insufficient to guarantee a sub-linear regret.

POSTER-192: InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Keywords: Vision-Language Models Instruction Tuning Zero-shot

Scores: [ 8 6 6 5 8 ]

Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the rich input distributions and task diversity resulting from the additional visual input. Although vision-language pretraining has been widely studied, vision-language instruction tuning remains under-explored. In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pretrained BLIP-2 models. We gather 26 publicly available datasets, covering a wide variety of tasks and capabilities, and transform them into instruction tuning format. Additionally, we introduce an instruction-aware Query Transformer, which extracts informative features tailored to the given instruction. Trained on 13 held-in datasets, InstructBLIP attains state-of-the-art zero-shot performance across all 13 held-out datasets, substantially outperforming BLIP-2 and larger Flamingo models. Our models also lead to state-of-the-art performance when finetuned on individual downstream tasks (e.g., 90.7% accuracy on ScienceQA questions with image contexts). Furthermore, we qualitatively demonstrate the advantages of InstructBLIP over concurrent multimodal models. All InstructBLIP models are open-source.

SPOTLIGHT-25: Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning

Keywords: reinforcement learning offline-to-online reinforcement learning offline reinforcement learning policy improvement policy constraint

Scores: [ 7 7 7 6 ]

Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each collected sample due to the significant variation in data quality across different states. To this end, we introduce Family Offline-to-Online RL (FamO2O), a simple yet effective framework that empowers existing algorithms to determine state-adaptive improvement-constraint balances. FamO2O utilizes a universal model to train a family of policies with different improvement/constraint intensities, and a balance model to select a suitable policy for each state. Theoretically, we prove that state-adaptive balances are necessary for achieving a higher policy performance upper bound. Empirically, extensive experiments show that FamO2O offers a statistically significant improvement over various existing methods, achieving state-of-the-art performance on the D4RL benchmark. Codes are available at

SPOTLIGHT-26: The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

Keywords: neural network invariance equivariance reparametrization riemannian geometry parameter space

Scores: [ 7 8 6 6 ]

POSTER-193: Revisiting the Minimalist Approach to Offline Reinforcement Learning

Keywords: Offline Reinforcement Learning

Scores: [ 5 6 7 7 ]

Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity. While these algorithms have led to noteworthy improvements, many incorporate seemingly minor design choices that impact their effectiveness beyond core algorithmic advances. However, the effect of these design choices on established baselines remains understudied. In this work, we aim to bridge this gap by conducting a retrospective analysis of recent works in offline RL and propose ReBRAC, a minimalistic algorithm that integrates such design elements built on top of the TD3+BC method. We evaluate ReBRAC on 51 datasets with both proprioceptive and visual state spaces using D4RL and V-D4RL benchmarks, demonstrating its state-of-the-art performance among ensemble-free methods in both offline and offline-to-online settings. To further illustrate the efficacy of these design choices, we perform a large-scale ablation study and hyperparameter sensitivity analysis on the scale of thousands of experiments.

POSTER-194: Online PCA in Converging Self-consistent Field Equations

Keywords: Self-consistent Field Equation Computational Science Online PCA

Scores: [ 6 7 6 5 ]

Self-consistent Field (SCF) equation is a type of nonlinear eigenvalue problem in which the matrix to be eigen-decomposed is a function of its own eigenvectors. It is of great significance in computational science for its connection to the Schrödinger equation. Traditional fixed-point iteration methods for solving such equations suffer from non-convergence issues. In this work, we present a novel perspective on such SCF equations as a principal component analysis (PCA) for non-stationary time series, in which a distribution and its own top principal components are mutually updated over time, and the equilibrium state of the model corresponds to the solution of the SCF equations. By the new perspective, online PCA techniques are able to engage in so as to enhance the convergence of the model towards the equilibrium state, acting as a new set of tools for converging the SCF equations. With several numerical adaptations, we then develop a new algorithm for converging the SCF equation, and demonstrated its high convergence capacity with experiments on both synthesized and real electronic structure scenarios.

POSTER-195: TransHP: Image Classification with Hierarchical Prompting

Keywords: hierarchical image classification hierarchical prompting vision transformer

Scores: [ 6 5 5 5 4 ]

This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task. Different from prior HIC methods, our hierarchical prompting is the first to explicitly inject ancestor-class information as a tokenized hint that benefits the descendant-class discrimination. We think it well imitates human visual recognition, i.e., humans may use the ancestor class as a prompt to draw focus on the subtle differences among descendant classes. We model this prompting mechanism into a Transformer with Hierarchical Prompting (TransHP). TransHP consists of three steps: 1) learning a set of prompt tokens to represent the coarse (ancestor) classes, 2) on-the-fly predicting the coarse class of the input image at an intermediate block, and 3) injecting the prompt token of the predicted coarse class into the intermediate feature. Though the parameters of TransHP maintain the same for all input images, the injected coarse-class prompt conditions (modifies) the subsequent feature extraction and encourages a dynamic focus on relatively subtle differences among the descendant classes. Extensive experiments show that TransHP improves image classification on accuracy (e.g., improving ViT-B/16 by +2.83% ImageNet classification accuracy), training data efficiency (e.g., +12.69% improvement under 10% ImageNet training data), and model explainability. Moreover, TransHP also performs favorably against prior HIC methods, showing that TransHP well exploits the hierarchical information. The code is available at:

Keywords: Reinforcement Learning Combinatorial Optimization TSP CVRP JSSP

Scores: [ 5 6 6 6 ]

Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a versatile framework for designing heuristics across a broad spectrum of problem domains. However, despite notable progress, RL has not yet supplanted industrial solvers as the go-to solution. Current approaches emphasize pre-training heuristics that construct solutions, but often rely on search procedures with limited variance, such as stochastically sampling numerous solutions from a single policy, or employing computationally expensive fine-tuning of the policy on individual problem instances. Building on the intuition that performant search at inference time should be anticipated during pre-training, we propose COMPASS, a novel RL approach that parameterizes a distribution of diverse and specialized policies conditioned on a continuous latent space. We evaluate COMPASS across three canonical problems - Travelling Salesman, Capacitated Vehicle Routing, and Job-Shop Scheduling - and demonstrate that our search strategy (i) outperforms state-of-the-art approaches in 9 out of 11 standard benchmarking tasks and (ii) generalizes better, surpassing all other approaches on a set of 18 procedurally transformed instance distributions.

SPOTLIGHT-27: Conditional score-based diffusion models for Bayesian inference in infinite dimensions

Keywords: score-based generative models diffusion models inverse problems bayesian inference infinite dimensions

Scores: [ 7 8 6 8 6 ]

Since their initial introduction, score-based diffusion models (SDMs) have been successfully applied to solve a variety of linear inverse problems in finite-dimensional vector spaces due to their ability to efficiently approximate the posterior distribution. However, using SDMs for inverse problems in infinite-dimensional function spaces has only been addressed recently, primarily through methods that learn the unconditional score. While this approach is advantageous for some inverse problems, it is mostly heuristic and involves numerous computationally costly forward operator evaluations during posterior sampling. To address these limitations, we propose a theoretically grounded method for sampling from the posterior of infinite-dimensional Bayesian linear inverse problems based on amortized conditional SDMs. In particular, we prove that one of the most successful approaches for estimating the conditional score in finite dimensions—the conditional denoising estimator—can also be applied in infinite dimensions. A significant part of our analysis is dedicated to demonstrating that extending infinite-dimensional SDMs to the conditional setting requires careful consideration, as the conditional score typically blows up for small times, contrarily to the unconditional score. We conclude by presenting stylized and large-scale numerical examples that validate our approach, offer additional insights, and demonstrate that our method enables large-scale, discretization-invariant Bayesian inference.

POSTER-197: Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do

Keywords: Learning in games Nash equilibrium Uncoupled Dynamics

Scores: [ 5 7 6 6 8 ]

The framework of multi-agent learning explores the dynamics of how an agent's strategies evolve in response to the evolving strategies of other agents. Of particular interest is whether or not agent strategies converge to well known solution concepts such as Nash Equilibrium (NE). In "higher order'' learning, agent dynamics include auxiliary states that can capture phenomena such as path dependencies. We introduce higher-order gradient play dynamics that resemble projected gradient ascent with auxiliary states. The dynamics are "payoff based'' and "uncoupled'' in that each agent's dynamics depend on its own evolving payoff and has no explicit dependence on the utilities of other agents. We first show that for any specific game with an isolated completely mixed-strategy NE, there exist higher-order gradient play dynamics that lead (locally) to that NE, both for the specific game and nearby games with perturbed utility functions. Conversely, we show that for any higher-order gradient play dynamics, there exists a game with a unique isolated completely mixed-strategy NE for which the dynamics do not lead to NE. Finally, we show that convergence to the mixed-strategy equilibrium in coordination games, comes at the expense of the dynamics being inherently internally unstable.

POSTER-198: On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Keywords: Weight Decay Regularization Optimization Deep Learning

Scores: [ 7 6 4 6 ]

Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs). While weight decay has attracted much attention, previous studies fail to discover some overlooked pitfalls on large gradient norms resulted by weight decay. In this paper, we discover that, weight decay can unfortunately lead to large gradient norms at the final phase (or the terminated solution) of training, which often indicates bad convergence and poor generalization. To mitigate the gradient-norm-centered pitfalls, we present the first practical scheduler for weight decay, called the Scheduled Weight Decay (SWD) method that can dynamically adjust the weight decay strength according to the gradient norm and significantly penalize large gradient norms during training. Our experiments also support that SWD indeed mitigates large gradient norms and often significantly outperforms the conventional constant weight decay strategy for Adaptive Moment Estimation (Adam).

POSTER-199: A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective

Keywords: multi-view learning, clustering

Scores: [ 6 7 6 7 6 ]

POSTER-200: Structured Voronoi Sampling

Keywords: Natural Language Processing Text Generation Controlled Generation MCMC HMC Langevin Dynamics

Scores: [ 5 7 6 8 6 7 ]

Gradient-based sampling algorithms have demonstrated their effectiveness in text generation, especially in the context of controlled text generation. However, there exists a lack of theoretically grounded and principled approaches for this task. In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods. We use discrete distributions given by language models to define densities and develop an algorithm based on Hamiltonian Monte Carlo to sample from them. We name our gradient-based technique Structured Voronoi Sampling (SVS). In an experimental setup where the reference distribution is known, we show that the empirical distribution of SVS samples is closer to the reference distribution compared to alternative sampling schemes. Furthermore, in a controlled generation task, SVS is able to generate fluent and diverse samples while following the control targets significantly better than other methods.

POSTER-201: Extremal Domain Translation with Neural Optimal Transport

Keywords: optimal transport partial optimal transport neural networks domain translation

Scores: [ 7 7 9 4 6 ]

In many unpaired image domain translation problems, e.g., style transfer or super-resolution, it is important to keep the translated image similar to its respective input image. We propose the extremal transport (ET) which is a mathematical formalization of the theoretically best possible unpaired translation between a pair of domains w.r.t. the given similarity function. Inspired by the recent advances in neural optimal transport (OT), we propose a scalable algorithm to approximate ET maps as a limit of partial OT maps. We test our algorithm on toy examples and on the unpaired image-to-image translation task. The code is publicly available at

POSTER-202: ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

Keywords: Auxiliary-Task Learning Negative Transfer

Scores: [ 7 6 7 4 6 6 ]

POSTER-203: A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing

Keywords: Compressed sensing generative models nonlinearity uniform recovery

Scores: [ 6 3 6 ]

In generative compressed sensing (GCS), we want to recover a signal \(\mathbf{x^*}\in\mathbb{R}^n\) from \(m\) measurements (\(m\ll n\)) using a generative prior \(\mathbf{x^*}\in G(\mathbb{B}_2^k(r))\), where \(G\) is typically an \(L\)-Lipschitz continuous generative model and \(\mathbb{B}_2^k(r)\) represents the radius-\(r\) \(\ell_2\)-ball in \(\mathbb{R}^k\). Under nonlinear measurements, most prior results are non-uniform, i.e., they hold with high probability for a fixed \(\mathbf{x^*}\) rather than for all \(\mathbf{x^*}\) simultaneously. In this paper, we build a unified framework to derive uniform recovery guarantees for nonlinear GCS where the observation model is nonlinear and possibly discontinuous or unknown. Our framework accommodates GCS with 1-bit/uniformly quantized observations and single index model as canonical examples. Specifically, using a single realization of the sensing ensemble and generalized Lasso, all \(\mathbf{x^*}\in G(\mathbb{B}_2^k(r))\) can be recovered up to an \(\ell_2\)-error at most \(\epsilon\) using roughly \(\tilde{O}({k}/{\epsilon^2})\) samples, with omitted logarithmic factors typically being dominated by \(\log L\). Notably, this almost coincides with existing non-uniform guarantees up to logarithmic factors, hence the uniformity costs very little. As part of our technical contributions, we introduce Lipschitz approximation to handle discontinuous observation models. We also develop a concentration inequality that produces tighter bound for product process whose index sets have low metric entropy. Experimental results are presented to corroborate our theory.

SPOTLIGHT-28: Faster Margin Maximization Rates for Generic Optimization Methods

Keywords: Implicit bias margin maximization zero-sum game online learning

Scores: [ 7 6 8 6 7 ]

First-order optimization methods tend to inherently favor certain solutions over others when minimizing a given training objective with multiple local optima. This phenomenon, known as \emph{implicit bias}, plays a critical role in understanding the generalization capabilities of optimization algorithms. Recent research has revealed that gradient-descent-based methods exhibit an implicit bias for the \(\ell_2\)-maximal margin classifier in the context of separable binary classification. In contrast, generic optimization methods, such as mirror descent and steepest descent, have been shown to converge to maximal margin classifiers defined by alternative geometries. However, while gradient-descent-based algorithms demonstrate fast implicit bias rates, the implicit bias rates of generic optimization methods have been relatively slow. To address this limitation, in this paper, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms. Our primary technique involves transforming a generic optimization algorithm into an online learning dynamic that solves a regularized bilinear game, providing a unified framework for analyzing the implicit bias of various optimization methods. The accelerated rates are derived leveraging the regret bounds of online learning algorithms within this game framework.

POSTER-204: Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

Keywords: Linear Mode Connectivity Permutation Invariance Optimization Landscape Science of Deep Learning

Scores: [ 7 5 6 8 7 ]

Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One of these phenomena, Linear Mode Connectivity (LMC), has gained considerable attention due to the intriguing observation that different solutions can be connected by a linear path in the parameter space while maintaining near-constant training and test losses. In this work, we introduce a stronger notion of linear connectivity, Layerwise Linear Feature Connectivity (LLFC), which says that the feature maps of every layer in different trained networks are also linearly connected. We provide comprehensive empirical evidence for LLFC across a wide range of settings, demonstrating that whenever two trained networks satisfy LMC (via either spawning or permutation methods), they also satisfy LLFC in nearly all the layers. Furthermore, we delve deeper into the underlying factors contributing to LLFC, which reveal new insights into the permutation approaches. The study of LLFC transcends and advances our understanding of LMC by adopting a feature-learning perspective.

POSTER-205: Data Pruning via Moving-one-Sample-out

Keywords: Data Valuation Deep Learning Data Pruning Coreset Selection.

Scores: [ 6 3 6 7 5 ]

In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which aims to identify and remove the least informative samples from the training set. The core insight behind MoSo is to determine the importance of each sample by assessing its impact on the optimal empirical risk. This is achieved by measuring the extent to which the empirical risk changes when a particular sample is excluded from the training set. Instead of using the computationally expensive leaving-one-out-retraining procedure, we propose an efficient first-order approximator that only requires gradient information from different training stages. The key idea behind our approximation is that samples with gradients that are consistently aligned with the average gradient of the training set are more informative and should receive higher scores, which could be intuitively understood as follows: if the gradient from a specific sample is consistent with the average gradient vector, it implies that optimizing the network using the sample will yield a similar effect on all remaining samples. Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios and achieves satisfactory performance across various settings. Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios and outperforms state-of-the-art methods by a large margin across various settings.

SPOTLIGHT-29: Imitation Learning from Imperfection: Theoretical Justifications and Algorithms

Keywords: imitation learning distribution shift policy optimization data selection

Scores: [ 6 7 7 6 ]

Imitation learning (IL) algorithms excel in acquiring high-quality policies from expert data for sequential decision-making tasks. But, their effectiveness is hampered when faced with limited expert data. To tackle this challenge, a novel framework called (offline) IL with supplementary data has been proposed, which enhances learning by incorporating an additional yet imperfect dataset obtained inexpensively from sub-optimal policies. Nonetheless, learning becomes challenging due to the potential inclusion of out-of-expert-distribution samples. In this work, we propose a mathematical formalization of this framework, uncovering its limitations. Our theoretical analysis reveals that a naive approach—applying the behavioral cloning (BC) algorithm concept to the combined set of expert and supplementary data—may fall short of vanilla BC, which solely relies on expert data. This deficiency arises due to the distribution shift between the two data sources. To address this issue, we propose a new importance-sampling-based technique for selecting data within the expert distribution. We prove that the proposed method eliminates the gap of the naive approach, highlighting its efficacy when handling imperfect data. Empirical studies demonstrate that our method outperforms previous state-of-the-art methods in tasks including robotic locomotion control, Atari video games, and image classification. Overall, our work underscores the potential of improving IL by leveraging diverse data sources through effective data selection.

POSTER-206: Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning

Keywords: Reinforcement Learning Graph Neural Network Cylindrical Algebraic Decomposition.

Scores: [ 5 6 7 8 ]

Cylindrical Algebraic Decomposition (CAD) is one of the pillar algorithms of symbolic computation, and its worst-case complexity is double exponential to the number of variables. Researchers found that variable order dramatically affects efficiency and proposed various heuristics. The existing learning-based methods are all supervised learning methods that cannot cope with diverse polynomial sets.This paper proposes two Reinforcement Learning (RL) approaches combined with Graph Neural Networks (GNN) for Suggesting Variable Order (SVO). One is GRL-SVO(UP), a branching heuristic integrated with CAD. The other is GRL-SVO(NUP), a fast heuristic providing a total order directly. We generate a random dataset and collect a real-world dataset from SMT-LIB. The experiments show that our approaches outperform state-of-the-art learning-based heuristics and are competitive with the best expert-based heuristics. Interestingly, our models show a strong generalization ability, working well on various datasets even if they are only trained on a 3-var random dataset. The source code and data are available at

POSTER-207: Exploiting Correlated Auxiliary Feedback in Parameterized Bandits

Keywords: Parameterized Bandits Auxiliary Feedback Control Variate Regret Minimization

Scores: [ 5 4 6 6 ]

We study a novel variant of the parameterized bandits problem in which the learner can observe additional auxiliary feedback that is correlated with the observed reward. The auxiliary feedback is readily available in many real-life applications, e.g., an online platform that wants to recommend the best-rated services to its users can observe the user's rating of service (rewards) and collect additional information like service delivery time (auxiliary feedback). In this paper, we first develop a method that exploits auxiliary feedback to build a reward estimator with tight confidence bounds, leading to a smaller regret. We then characterize the regret reduction in terms of the correlation coefficient between reward and its auxiliary feedback. Experimental results in different settings also verify the performance gain achieved by our proposed method.

POSTER-208: Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity

Keywords: Transformer NMDA long-term memory reference memory memory consolidation

Scores: [ 7 6 3 5 ]

The hippocampus plays a critical role in learning, memory, and spatial representation, processes that depend on the NMDA receptor (NMDAR). Inspired by recent findings that compare deep learning models to the hippocampus, we propose a new nonlinear activation function that mimics NMDAR dynamics. NMDAR-like nonlinearity shifts short-term working memory into long-term reference memory in transformers, thus enhancing a process that is similar to memory consolidation in the mammalian brain. We design a navigation task assessing these two memory functions and show that manipulating the activation function (i.e., mimicking the Mg$^{2+}$-gating of NMDAR) disrupts long-term memory processes. Our experiments suggest that place cell-like functions and reference memory reside in the feed-forward network layer of transformers and that nonlinearity drives these processes. We discuss the role of NMDAR-like nonlinearity in establishing this striking resemblance between transformer architecture and hippocampal spatial representation.

SPOTLIGHT-30: Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization

Keywords: convex optimization quasi-Newton methods Monteiro-Svaiter acceleration Nesterov's accelerated gradient online learning

Scores: [ 8 6 5 7 ]

In this paper, we propose an accelerated quasi-Newton proximal extragradient method for solving unconstrained smooth convex optimization problems. With access only to the gradients of the objective, we prove that our method can achieve a convergence rate of \(\mathcal{O}\bigl(\min\\{\frac{1}{k^2}, \frac{\sqrt{d\log k}}{k^{2.5}}\\}\bigr)\), where \(d\) is the problem dimension and \(k\) is the number of iterations. In particular, in the regime where \(k = \mathcal{O}(d)\), our method matches the optimal rate of \(\mathcal{O}(\frac{1}{k^2})\) by Nesterov's accelerated gradient (NAG). Moreover, in the the regime where \(k = \Omega(d \log d)\), it outperforms NAG and converges at a faster rate of \(\mathcal{O}\bigl(\frac{\sqrt{d\log k}}{k^{2.5}}\bigr)\). To the best of our knowledge, this result is the first to demonstrate a provable gain for a quasi-Newton-type method over NAG in the convex setting. To achieve such results, we build our method on a recent variant of the Monteiro-Svaiter acceleration framework and adopt an online learning perspective to update the Hessian approximation matrices, in which we relate the convergence rate of our method to the dynamic regret of a specific online convex optimization problem in the space of matrices.

POSTER-209: Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

Keywords: stochastic optimization gradient-free optimization zero-order oracle gradient clipping infinite variance

Scores: [ 6 5 7 7 6 ]

In this paper, we consider non-smooth stochastic convex optimization with two function evaluations per round under infinite noise variance. In the classical setting when noise has finite variance, an optimal algorithm, built upon the batched accelerated gradient method, was proposed in (Gasnikov et. al., 2022). This optimality is defined in terms of iteration and oracle complexity, as well as the maximal admissible level of adversarial noise. However, the assumption of finite variance is burdensome and it might not hold in many practical scenarios. To address this, we demonstrate how to adapt a refined clipped version of the accelerated gradient (Stochastic Similar Triangles) method from (Sadiev et al., 2023) for a two-point zero-order oracle. This adaptation entails extending the batching technique to accommodate infinite variance — a non-trivial task that stands as a distinct contribution of this paper.

POSTER-210: Generalized Weighted Path Consistency for Mastering Atari Games

Keywords: Monte Carlo Tree Search Reinforcement learning Path consistency.

Scores: [ 7 7 4 5 4 ]

Reinforcement learning with the help of neural-guided search consumes huge computational resources to achieve remarkable performance. Path consistency (PC), i.e., \(f\) values on one optimal path should be identical, was previously imposed on MCTS by PCZero to improve the learning efficiency of AlphaZero. Not only PCZero still lacks a theoretical support but also considers merely board games. In this paper, PCZero is generalized into GW-PCZero for real applications with non-zero immediate reward. A weighting mechanism is introduced to reduce the variance caused by scouting's uncertainty on the \(f\) value estimation. For the first time, it is theoretically proved that neural-guided MCTS is guaranteed to find the optimal solution under the constraint of PC. Experiments are conducted on the Atari $100$k benchmark with \(26\) games and GW-PCZero achieves \(198\%\) mean human performance, higher than the state-of-the-art EfficientZero's \(194\\%\), while consuming only \(25\\%\) of the computational resources consumed by EfficientZero.

POSTER-211: Self-supervised video pretraining yields robust and more human-aligned visual representations

Keywords: self-supervised learning contrastive video pretraining representation learning visual representation human alignment robustness shape-bias saliency

Scores: [ 6 7 6 5 5 6 ]

Humans learn powerful representations of objects and scenes by observing how they evolve over time. Yet, outside of specific tasks that require explicit temporal understanding, static image pretraining remains the dominant paradigm for learning visual foundation models. We question this mismatch, and ask whether video pretraining can yield visual representations that bear the hallmarks of human perception: generalisation across tasks, robustness to perturbations, and consistency with human judgements. To that end we propose a novel procedure for curating videos, and develop a contrastive framework which learns from the complex transformations therein. This simple paradigm for distilling knowledge from videos, called VITO, yields general representations that far outperform prior video pretraining methods on image understanding tasks, and image pretraining methods on video understanding tasks. Moreover, VITO representations are significantly more robust to natural and synthetic deformations than image-, video-, and adversarially-trainedones. Finally, VITO’s predictions are strongly aligned with human judgements, surpassing models that were specifically trained for that purpose. Together, these results suggest that video pretraining could be a simple way of learning unified, robust, and human-aligned representations of the visual world.

POSTER-212: On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data

Keywords: Deep Graph Networks Graph Neural Networks Graph Representation Learning Nearest Neighbors Node Classification Tabular Data

Scores: [ 5 5 6 5 6 7 ]

Researchers have used nearest neighbor graphs to transform classical machine learning problems on tabular data into node classification tasks to solve with graph representation learning methods. Such artificial structures often reflect the homophily assumption, believed to be a key factor in the performances of deep graph networks. In light of recent results demystifying these beliefs, we introduce a theoretical framework to understand the benefits of Nearest Neighbor (NN) graphs when a graph structure is missing. We formally analyze the Cross-Class Neighborhood Similarity (CCNS), used to empirically evaluate the usefulness of structures, in the context of nearest neighbor graphs. Moreover, we study the class separability induced by deep graph networks on a k-NN graph. Motivated by the theory, our quantitative experiments demonstrate that, under full supervision, employing a k-NN graph offers no benefits compared to a structure-agnostic baseline. Qualitative analyses suggest that our framework is good at estimating the CCNS and hint at k-NN graphs never being useful for such classification tasks under full supervision, thus advocating for the study of alternative graph construction techniques in combination with deep graph networks.

POSTER-213: Neural Algorithmic Reasoning Without Intermediate Supervision

Keywords: neural algorithmic reasoning graph neural networks self-supervised regularization

Scores: [ 6 4 5 7 7 ]

Neural algorithmic reasoning is an emerging area of machine learning focusing on building models that can imitate the execution of classic algorithms, such as sorting, shortest paths, etc. One of the main challenges is to learn algorithms that are able to generalize to out-of-distribution data, in particular with significantly larger input sizes. Recent work on this problem has demonstrated the advantages of learning algorithms step-by-step, giving models access to all intermediate steps of the original algorithm. In this work, we instead focus on learning neural algorithmic reasoning only from the input-output pairs without appealing to the intermediate supervision. We propose simple but effective architectural improvements and also build a self-supervised objective that can regularise intermediate computations of the model without access to the algorithm trajectory. We demonstrate that our approach is competitive to its trajectory-supervised counterpart on tasks from the CLRS Algorithmic Reasoning Benchmark and achieves new state-of-the-art results for several problems, including sorting, where we obtain significant improvements. Thus, learning without intermediate supervision is a promising direction for further research on neural reasoners.

POSTER-214: An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits

Keywords: bandit linear bandit best of both worlds exploration by optimization

Scores: [ 6 5 6 7 ]

In this paper, we consider how to construct best-of-both-worlds linear bandit algorithms that achieve nearly optimal performance for both stochastic and adversarial environments. For this purpose, we show that a natural approach referred to as exploration by optimization [Lattimore and Szepesvári, 2020] works well. Specifically, an algorithm constructed using this approach achieves \(O(d \sqrt{ T \log{T}})\)-regret in adversarial environments and \(O(\frac{d^2 \log T}{\Delta_{\min}} )\)-regret in stochastic environments. Symbols \(d\), \(T\) and \(\Delta_{\min}\) here represent the dimensionality of the action set, the time horizon, and the minimum sub-optimality gap, respectively. We also show that this algorithm has even better theoretical guarantees for important special cases including the multi-armed bandit problem and multitask bandits.

POSTER-215: Reflexion: language agents with verbal reinforcement learning

Keywords: language model reasoning decision making programming

Scores: [ 7 6 4 7 7 ]

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose \emph{Reflexion}, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain their own reflective text in an episodic memory buffer to induce better decision-making in subsequent trials. Reflexion is flexible enough to incorporate various types (scalar values or free-form language) and sources (external or internally simulated) of feedback signals, and obtains significant improvements over a baseline agent across diverse tasks (sequential decision-making, coding, language reasoning). For example, Reflexion achieves a 91% pass@1 accuracy on the HumanEval coding benchmark, surpassing the previous state-of-the-art GPT-4 that achieves 80%. We also conduct ablation and analysis studies using different feedback signals, feedback incorporation methods, and agent types, and provide insights into how they affect performance. We release all code, demos, and datasets at \url{}.

SPOTLIGHT-31: MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

Keywords: multiview; image generation; generative model; diffusion models

Scores: [ 7 6 7 5 ]

This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth maps and poses). Unlike prior methods that rely on iterative image warping and inpainting, MVDiffusion simultaneously generates all images with a global awareness, effectively addressing the prevalent error accumulation issue. At its core, MVDiffusion processes perspective images in parallel with a pre-trained text-to-image diffusion model, while integrating novel correspondence-aware attention layers to facilitate cross-view interactions. For panorama generation, while only trained with 10k panoramas, MVDiffusion is able to generate high-resolution photorealistic images for arbitrary texts or extrapolate one perspective image to a 360-degree view. For multi-view depth-to-image generation, MVDiffusion demonstrates state-of-the-art performance for texturing a scene mesh. The project page is at

SPOTLIGHT-32: Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model

Keywords: neural collapse unconstrained features model deep learning

Scores: [ 7 7 6 6 ]

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of NC to earlier layers of neural networks. However, while the NC in the last layer is well studied theoretically, much less is known about its multi-layered counterpart - deep neural collapse (DNC). In particular, existing work focuses either on linear layers or only on the last two layers at the price of an extra assumption. Our work fills this gap by generalizing the established analytical framework for NC - the unconstrained features model - to multiple non-linear layers. Our key technical contribution is to show that, in a deep unconstrained features model, the unique global optimum for binary classification exhibits all the properties typical of DNC. This explains the existing experimental evidence of DNC. We also empirically show that (i) by optimizing deep unconstrained features models via gradient descent, the resulting solution agrees well with our theory, and (ii) trained networks recover the unconstrained features suitable for the occurrence of DNC, thus supporting the validity of this modeling principle.

POSTER-216: Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

Keywords: distributional reinforcement learning risk

Scores: [ 6 4 5 7 7 ]

Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased data collection and hinder convergence or performance. In this paper, we present a novel distributional reinforcement learning that selects actions by randomizing risk criterion without losing the risk-neutral objective. We provide a perturbed distributional Bellman optimality operator by distorting the risk measure. Also,we prove the convergence and optimality of the proposed method with the weaker contraction property. Our theoretical results support that the proposed method does not fall into biased exploration and is guaranteed to converge to an optimal return. Finally, we empirically show that our method outperforms other existing distribution-based algorithms in various environments including Atari 55 games.

POSTER-217: End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics

Keywords: Diffusion Variational VAE LDM Physics Unfolding

Scores: [ 7 4 9 4 ]

High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions or measurements from other detectors. Methods to solve this inverse problem of mapping detector observations to theoretical quantities of the underlying collision are essential parts of many physics analyses at the LHC. We investigate and compare various generative deep learning methods to approximate this inverse mapping. We introduce a novel unified architecture, termed latent variational diffusion models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. We demonstrate the effectiveness of this approach for reconstructing global distributions of theoretical kinematic quantities, as well as for ensuring the adherence of the learned posterior distributions to known physics constraints. Our unified approach achieves a distribution-free distance to the truth of over 20 times smaller than non-latent state-of-the-art baseline and 3 times smaller than traditional latent diffusion models.

POSTER-218: Adaptive Algorithms for Relaxed Pareto Set Identification

Keywords: bandit pure-exploration pareto front pareto set

Scores: [ 6 6 5 6 ]

In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model. As the sample complexity to identify the exact Pareto set can be very large, a relaxation allowing to output some additional near-optimal arms has been studied. In this work we also tackle alternative relaxations that allow instead to identify a relevant \emph{subset} of the Pareto set. Notably, we propose a single sampling strategy, called Adaptive Pareto Exploration, that can be used in conjunction with different stopping rules to take into account different relaxations of the Pareto Set Identification problem. We analyze the sample complexity of these different combinations, quantifying in particular the reduction in sample complexity that occurs when one seeks to identify at most \(k\) Pareto optimal arms. We showcase the good practical performance of Adaptive Pareto Exploration on a real-world scenario, in which we adaptively explore several vaccination strategies against Covid-19 in order to find the optimal ones when multiple immunogenicity criteria are taken into account.

POSTER-219: Deep Equilibrium Based Neural Operators for Steady-State PDEs

Keywords: Deep Equilibrium Models Partial Differential Equations Neural Operators

Scores: [ 6 5 9 7 ]

Data-driven machine learning approaches are being increasingly used to solve partial differential equations (PDEs). They have shown particularly striking successes when training an operator, which takes as input a PDE in some family, and outputs its solution. However, the architectural design space, especially given structural knowledge of the PDE family of interest, is still poorly understood. We seek to remedy this gap by studying the benefits of weight-tied neural network architectures for steady-state PDEs. To achieve this, we first demonstrate that the solution of most steady-state PDEs can be expressed as a fixed point of a non-linear operator. Motivated by this observation, we propose FNO-DEQ, a deep equilibrium variant of the FNO architecture that directly solves for the solution of a steady-state PDE as the infinite-depth fixed point of an implicit operator layer using a black-box root solver and differentiates analytically through this fixed point resulting in \(\mathcal{O}(1)\) training memory. Our experiments indicate that FNO-DEQ-based architectures outperform FNO-based baselines with \(4\times\) the number of parameters in predicting the solution to steady-state PDEs such as Darcy Flow and steady-state incompressible Navier-Stokes. Finally, we show FNO-DEQ is more robust when trained with datasets with more noisy observations than the FNO-based baselines, demonstrating the benefits of using appropriate inductive biases in architectural design for different neural network based PDE solvers. Further, we show a universal approximation result that demonstrates that FNO-DEQ can approximate the solution to any steady-state PDE that can be written as a fixed point equation.

POSTER-220: Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Keywords: Combinatorial Optimization Reinforcement Learning TSP CVRP JSSP

Scores: [ 6 5 8 5 ]

POSTER-221: Improving Adversarial Robustness via Information Bottleneck Distillation

Keywords: Information Bottleneck Adversarial training Adversarial robustness Knowledge distillation

Scores: [ 6 5 7 5 5 ]

Previous studies have shown that optimizing the information bottleneck can significantly improve the robustness of deep neural networks. Our study closely examines the information bottleneck principle and proposes an Information Bottleneck Distillation approach. This specially designed, robust distillation technique utilizes prior knowledge obtained from a robust pre-trained model to boost information bottlenecks. Specifically, we propose two distillation strategies that align with the two optimization processes of the information bottleneck. Firstly, we use a robust soft-label distillation method to increase the mutual information between latent features and output prediction. Secondly, we introduce an adaptive feature distillation method that automatically transfers relevant knowledge from the teacher model to the student model, thereby reducing the mutual information between the input and latent features. We conduct extensive experiments to evaluate our approach's robustness against state-of-the-art adversarial attackers such as PGD-attack and AutoAttack. Our experimental results demonstrate the effectiveness of our approach in significantly improving adversarial robustness. Our code is available at

POSTER-222: UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Keywords: Image Generation Multi-modal HyperNet

Scores: [ 5 5 6 5 6 ]

Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages. However, they often fall short in generating images with spatial, structural, or geometric controls. The integration of such controls, which can accommodate various visual conditions in a single unified model, remains an unaddressed challenge. In response, we introduce UniControl, a new generative foundation model that consolidates a wide array of controllable condition-to-image (C2I) tasks within a singular framework, while still allowing for arbitrary language prompts. UniControl enables pixel-level-precise image generation, where visual conditions primarily influence the generated structures and language prompts guide the style and context. To equip UniControl with the capacity to handle diverse visual conditions, we augment pretrained text-to-image diffusion models and introduce a task-aware HyperNet to modulate the diffusion models, enabling the adaptation to different C2I tasks simultaneously. Trained on nine unique C2I tasks, UniControl demonstrates impressive zero-shot generation abilities with unseen visual conditions. Experimental results show that UniControl often surpasses the performance of single-task-controlled methods of comparable model sizes. This control versatility positions UniControl as a significant advancement in the realm of controllable visual generation.

POSTER-223: MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues

Keywords: 3D detection deep learning autonomous driving

Scores: [ 4 5 5 7 ]

Monocular 3D detection of vehicle and infrastructure sides are two important topics in autonomous driving. Due to diverse sensor installations and focal lengths, researchers are faced with the challenge of constructing algorithms for the two topics based on different prior knowledge. In this paper, by taking into account the diversity of pitch angles and focal lengths, we propose a unified optimization target named normalized depth, which realizes the unification of 3D detection problems for the two sides. Furthermore, to enhance the accuracy of monocular 3D detection, 3D normalized cube depth of obstacle is developed to promote the learning of depth information. We posit that the richness of depth clues is a pivotal factor impacting the detection performance on both the vehicle and infrastructure sides. A richer set of depth clues facilitates the model to learn better spatial knowledge, and the 3D normalized cube depth offers sufficient depth clues. Extensive experiments demonstrate the effectiveness of our approach. Without introducing any extra information, our method, named MonoUNI, achieves state-of-the-art performance on five widely used monocular 3D detection benchmarks, including Rope3D and DAIR-V2X-I for the infrastructure side, KITTI and Waymo for the vehicle side, and nuScenes for the cross-dataset evaluation.

POSTER-224: H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection

Keywords: Oriented object detection self-supervised learning

Scores: [ 7 5 7 7 ]

With the rapidly increasing demand for oriented object detection, e.g. in autonomous driving and remote sensing, the recently proposed paradigm involving weakly-supervised detector H2RBox for learning rotated box (RBox) from the more readily-available horizontal box (HBox) has shown promise. This paper presents H2RBox-v2, to further bridge the gap between HBox-supervised and RBox-supervised oriented object detection. Specifically, we propose to leverage the reflection symmetry via flip and rotate consistencies, using a weakly-supervised network branch similar to H2RBox, together with a novel self-supervised branch that learns orientations from the symmetry inherent in visual objects. The detector is further stabilized and enhanced by practical techniques to cope with peripheral issues e.g. angular periodicity. To our best knowledge, H2RBox-v2 is the first symmetry-aware self-supervised paradigm for oriented object detection. In particular, our method shows less susceptibility to low-quality annotation and insufficient training data compared to H2RBox. Specifically, H2RBox-v2 achieves very close performance to a rotation annotation trained counterpart -- Rotated FCOS: 1) DOTA-v1.0/1.5/2.0: 72.31%/64.76%/50.33% vs. 72.44%/64.53%/51.77%; 2) HRSC: 89.66% vs. 88.99%; 3) FAIR1M: 42.27% vs. 41.25%.

POSTER-225: Egocentric Planning for Scalable Embodied Task Achievement

Keywords: Embodied AI High-Level Actions Symbolic Reasoning Replanning ALFRED Challenge Flexible Task Achievement User-Goal Understanding Object Types and Actions Perception Grounding

Scores: [ 6 6 4 7 5 ]

Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing across object types and executing suitable actions to accomplish tasks. Furthermore, agents should exhibit robustness, minimizing the execution of illegal actions. In this work, we present Egocentric Planning, an innovative approach that combines symbolic planning and Object-oriented POMDPs to solve tasks in complex environments, harnessing existing models for visual perception and natural language processing. We evaluated our approach in ALFRED, a simulated environment designed for domestic tasks, and demonstrated its high scalability, achieving an impressive 36.07% unseen success rate in the ALFRED benchmark and winning the ALFRED challenge at CVPR Embodied AI workshop. Our method requires reliable perception and the specification or learning of a symbolic description of the preconditions and effects of the agent's actions, as well as what object types reveal information about others. It can naturally scale to solve new tasks beyond ALFRED, as long as they can be solved using the available skills. This work offers a solid baseline for studying end-to-end and hybrid methods that aim to generalize to new tasks, including recent approaches relying on LLMs, but often struggle to scale to long sequences of actions or produce robust plans for novel tasks.

POSTER-226: Temporal Continual Learning with Prior Compensation for Human Motion Prediction

Keywords: Human Motion Prediction; Temporal Continual Learning; Prior Compensation Factor

Scores: [ 5 5 5 5 6 ]

Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning of short-term predictions is hindered by the focus on long-term predictions, and the incorporation of prior information from past predictions into subsequent predictions is limited. In this paper, we introduce a novel multi-stage training framework called Temporal Continual Learning (TCL) to address the above challenges. To better preserve prior information, we introduce the Prior Compensation Factor (PCF). We incorporate it into the model training to compensate for the lost prior information. Furthermore, we derive a more reasonable optimization objective through theoretical derivation. It is important to note that our TCL framework can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on four HMP benchmark datasets demonstrate the effectiveness and flexibility of TCL. The code is available at

POSTER-227: Online robust non-stationary estimation

Keywords: Estimation heavy-tails distribution shifts regret

Scores: [ 7 4 4 8 7 ]

The real-time estimation of time-varying parameters from high-dimensional, heavy-tailed and corrupted data-streams is a common sub-routine in systems ranging from those for network monitoring and anomaly detection to those for traffic scheduling in data-centers. For estimation tasks that can be cast as minimizing a strongly convex loss function, we prove that an appropriately tuned version of the {\ttfamily clipped Stochastic Gradient Descent} (SGD) is simultaneously {\em(i)} adaptive to drift, {\em (ii)} robust to heavy-tailed inliers and arbitrary corruptions, {\em(iii)} requires no distributional knowledge and {\em (iv)} can be implemented in an online streaming fashion. All prior estimation algorithms have only been proven to posses a subset of these practical desiderata. A observation we make is that, neither the \(\mathcal{O}\left(\frac{1}{t}\right)\) learning rate for {\ttfamily clipped SGD} known to be optimal for strongly convex loss functions of a \emph{stationary} data-stream, nor the \(\mathcal{O}(1)\) learning rate known to be optimal for being adaptive to drift in a \emph{noiseless} environment can be used. Instead, a learning rate of \(T^{-\alpha}\) for $ \alpha < 1$ where \(T\) is the stream-length is needed to balance adaptivity to potential drift and to combat noise. We develop a new inductive argument and combine it with a martingale concentration result to derive high-probability under \emph{any learning rate} on data-streams exhibiting \emph{arbitrary distribution shift} - a proof strategy that may be of independent interest. Further, using the classical doubling-trick, we relax the knowledge of the stream length \(T\). Ours is the first online estimation algorithm that is provably robust to heavy-tails, corruptions and distribution shift simultaneously. We complement our theoretical results empirically on synthetic and real data.

SPOTLIGHT-33: Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

Keywords: Transformers Context-pruning Efficient Transformer

Scores: [ 7 7 7 7 ]

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens in the sequence, thus incurring a quadratic cost. In this study, we present a novel approach that dynamically prunes contextual information while preserving the model's expressiveness, resulting in reduced memory and computational requirements during inference. Our method employs a learnable mechanism that determines which uninformative tokens can be dropped from the context at any point across the generation process. By doing so, our approach not only addresses performance concerns but also enhances interpretability, providing valuable insight into the model's decision-making process. Our technique can be applied to existing pre-trained models through a straightforward fine-tuning process, and the pruning strength can be specified by a sparsity parameter. Notably, our empirical findings demonstrate that we can effectively prune up to 80% of the context without significant performance degradation on downstream tasks, offering a valuable tool for mitigating inference costs. Our reference implementation achieves up to \(2\times\) increase in inference throughput and even greater memory savings.

POSTER-228: Training Your Image Restoration Network Better with Random Weight Network as Optimization Function

Keywords: Image restoration low-light image enhancement image de-noising

Scores: [ 8 8 4 7 ]

The blooming progress made in deep learning-based image restoration has been largely attributed to the availability of high-quality, large-scale datasets and advanced network structures. However, optimization functions such as L_1 and L_2 are still de facto. In this study, we propose to investigate new optimization functions to improve image restoration performance. Our key insight is that ``random weight network can be acted as a constraint for training better image restoration networks''. However, not all random weight networks are suitable as constraints. We draw inspiration from Functional theory and show that alternative random weight networks should be represented in the form of a strict mathematical manifold. We explore the potential of our random weight network prototypes that satisfy this requirement: Taylor's unfolding network, invertible neural network, central difference convolution, and zero-order filtering. We investigate these prototypes from four aspects: 1) random weight strategies, 2) network architectures, 3) network depths, and 4) combinations of random weight networks. Furthermore, we devise the random weight in two variants: the weights are randomly initialized only once during the entire training procedure, and the weights are randomly initialized in each training epoch. Our approach can be directly integrated into existing networks without incurring additional training and testing computational costs. We perform extensive experiments across multiple image restoration tasks, including image denoising, low-light image enhancement, and guided image super-resolution to demonstrate the consistent performance gains achieved by our method. Upon acceptance of this paper, we will release the code.

SPOTLIGHT-34: Can semi-supervised learning use all the data effectively? A lower bound perspective

Keywords: semi-supervised learning statistical lower bound

Scores: [ 7 6 5 8 ]

Prior theoretical and empirical works have established that semi-supervised learning algorithms can leverage the unlabeled data to improve over the labeled sample complexity of supervised learning (SL) algorithms. However, existing theoretical work focuses on regimes where the unlabeled data is sufficient to learn a good decision boundary using unsupervised learning (UL) alone. This begs the question: Can SSL algorithms simultaneously improve upon both UL and SL? To this end, we derive a tight lower bound for 2-Gaussian mixture models that explicitly depends on the labeled and the unlabeled dataset size as well as the signal-to-noise ratio of the mixture distribution. Surprisingly, our result implies that no SSL algorithm improves upon the minimax-optimal statistical error rates of SL or UL algorithms for these distributions. Nevertheless, in our real-world experiments, SSL algorithms can often outperform UL and SL algorithms. In summary, our work suggests that while it is possible to prove the performance gains of SSL algorithms, this would require careful tracking of constants in the theoretical analysis.

POSTER-229: All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

Keywords: point cloud segmentation weak supervision

Scores: [ 6 7 5 7 5 ]

Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning.Existing methods often rely on empirical label selection strategies, such as confidence thresholding, to generate beneficial pseudo-labels for model training.This approach may, however, hinder the comprehensive exploitation of unlabeled data points.We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly.To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.More specifically, our method introduces an Entropy Regularization loss and a Distribution Alignment loss for weakly supervised learning in 3D segmentation tasks, resulting in an ERDA learning strategy.Interestingly, by using KL distance to formulate the distribution alignment loss, it reduces to a deceptively simple cross-entropy-based loss which optimizes both the pseudo-label generation network and the 3D segmentation network simultaneously.Despite the simplicity, our method promisingly improves the performance.We validate the effectiveness through extensive experiments on various baselines and large-scale datasets.Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings.Remarkably, our method can outperform fully-supervised baselines using only 1% of true annotations.Code and model will be made publicly available at

POSTER-230: Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

Keywords: Graph Data Augmentation Graph Mixup Fused Gromov Wasserstein

Scores: [ 5 6 4 6 6 ]

Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a "midpoint" of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from \(\mathcal{O}(t^{-1})\) to \(\mathcal{O}(t^{-2})\). Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that \mname\xspace effectively improves the generalizability and robustness of GNNs. Codes are available at

POSTER-231: Optimal approximation using complex-valued neural networks

Keywords: complex-valued neural networks approximation rates

Scores: [ 7 7 5 3 ]

POSTER-232: PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

Keywords: Hyperparameter Optimization Deep Learning

Scores: [ 5 7 6 6 ]

Hyperparameters of Deep Learning (DL) pipelines are crucial for their downstream performance. While a large number of methods for Hyperparameter Optimization (HPO) have been developed, their incurred costs are often untenable for modern DL.Consequently, manual experimentation is still the most prevalent approach to optimize hyperparameters, relying on the researcher's intuition, domain knowledge, and cheap preliminary explorations.To resolve this misalignment between HPO algorithms and DL researchers, we propose PriorBand, an HPO algorithm tailored to DL, able to utilize both expert beliefs and cheap proxy tasks. Empirically, we demonstrate PriorBand's efficiency across a range of DL benchmarks and show its gains under informative expert input and robustness against poor expert beliefs.

POSTER-233: Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees

Keywords: Concept drift Continual learning Minimax classification Performance guarantees

Scores: [ 5 5 5 7 6 ]

For a sequence of classification tasks that arrive over time, it is common that tasks are evolving in the sense that consecutive tasks often have a higher similarity. The incremental learning of a growing sequence of tasks holds promise to enable accurate classification even with few samples per task by leveraging information from all the tasks in the sequence (forward and backward learning). However, existing techniques developed for continual learning and concept drift adaptation are either designed for tasks with time-independent similarities or only aim to learn the last task in the sequence. This paper presents incremental minimax risk classifiers (IMRCs) that effectively exploit forward and backward learning and account for evolving tasks. In addition, we analytically characterize the performance improvement provided by forward and backward learning in terms of the tasks’ expected quadratic change and the number of tasks. The experimental evaluation shows that IMRCs can result in a significant performance improvement, especially for reduced sample sizes.

POSTER-234: Sample-efficient Multi-objective Molecular Optimization with GFlowNets

Keywords: drug discovery multi-objective molecular optimization Bayesian optimization generative flow networks

Scores: [ 6 5 6 5 ]

Many crucial scientific problems involve designing novel molecules with desired properties, which can be formulated as a black-box optimization problem over the discrete chemical space. In practice, multiple conflicting objectives and costly evaluations (e.g., wet-lab experiments) make the diversity of candidates paramount. Computational methods have achieved initial success but still struggle with considering diversity in both objective and search space. To fill this gap, we propose a multi-objective Bayesian optimization (MOBO) algorithm leveraging the hypernetwork-based GFlowNets (HN-GFN) as an acquisition function optimizer, with the purpose of sampling a diverse batch of candidate molecular graphs from an approximate Pareto front. Using a single preference-conditioned hypernetwork, HN-GFN learns to explore various trade-offs between objectives. We further propose a hindsight-like off-policy strategy to share high-performing molecules among different preferences in order to speed up learning for HN-GFN. We empirically illustrate that HN-GFN has adequate capacity to generalize over preferences. Moreover, experiments in various real-world MOBO settings demonstrate that our framework predominantly outperforms existing methods in terms of candidate quality and sample efficiency. The code is available at

POSTER-235: Energy-Based Sliced Wasserstein Distance

Keywords: Sliced Wasserstein Monte Carlo Methods Point-Cloud Optimal Transport

Scores: [ 6 6 6 5 ]

The sliced Wasserstein (SW) distance has been widely recognized as a statistically effective and computationally efficient metric between two probability measures. A key component of the SW distance is the slicing distribution. There are two existing approaches for choosing this distribution. The first approach is using a fixed prior distribution. The second approach is optimizing for the best distribution which belongs to a parametric family of distributions and can maximize the expected distance. However, both approaches have their limitations. A fixed prior distribution is non-informative in terms of highlighting projecting directions that can discriminate two general probability measures. Doing optimization for the best distribution is often expensive and unstable. Moreover, designing the parametric family of the candidate distribution could be easily misspecified. To address the issues, we propose to design the slicing distribution as an energy-based distribution that is parameter-free and has the density proportional to an energy function of the projected one-dimensional Wasserstein distance. We then derive a novel sliced Wasserstein variant, energy-based sliced Waserstein (EBSW) distance, and investigate its topological, statistical, and computational properties via importance sampling, sampling importance resampling, and Markov Chain methods. Finally, we conduct experiments on point-cloud gradient flow, color transfer, and point-cloud reconstruction to show the favorable performance of the EBSW.

POSTER-236: Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

Keywords: data-free subnetwork task-incremental learning knowledge transfer mask

Scores: [ 4 6 6 4 5 ]

As there exist competitive subnetworks within a dense network in concert with Lottery Ticket Hypothesis, we introduce a novel neuron-wise task incremental learning method, namely Data-free Subnetworks (DSN), which attempts to enhance the elastic knowledge transfer across the tasks that sequentially arrive. Specifically, DSN primarily seeks to transfer knowledge to the new coming task from the learned tasks by selecting the affiliated weights of a small set of neurons to be activated, including the reused neurons from prior tasks via neuron-wise masks. And it also transfers possibly valuable knowledge to the earlier tasks via data-free replay. Especially, DSN inherently relieves the catastrophic forgetting and the unavailability of past data or possible privacy concerns. The comprehensive experiments conducted on four benchmark datasets demonstrate the effectiveness of the proposed DSN in the context of task-incremental learning by comparing it to several state-of-the-art baselines. In particular, DSN enables the knowledge transfer to the earlier tasks, which is often overlooked by prior efforts.

POSTER-237: Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation

Keywords: Active Learning LiDAR Semantic Segmentation Domain Adaptation

Scores: [ 6 6 6 6 7 ]

Active learning, a label-efficient paradigm, empowers models to interactively query an oracle for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem from the sheer volume of point clouds, rendering annotation labor-intensive and cost-prohibitive. This paper presents Annotator, a general and efficient active learning baseline, in which a voxel-centric online selection strategy is tailored to efficiently probe and annotate the salient and exemplar voxel girds within each LiDAR scan, even under distribution shift. Concretely, we first execute an in-depth analysis of several common selection strategies such as Random, Entropy, Margin, and then develop voxel confusion degree (VCD) to exploit the local topology relations and structures of point clouds. Annotator excels in diverse settings, with a particular focus on active learning (AL), active source-free domain adaptation (ASFDA), and active domain adaptation (ADA). It consistently delivers exceptional performance across LiDAR semantic segmentation benchmarks, spanning both simulation-to-real and real-to-real scenarios. Surprisingly, Annotator exhibits remarkable efficiency, requiring significantly fewer annotations, e.g., just labeling five voxels per scan in the SynLiDAR → SemanticKITTI task. This results in impressive performance, achieving 87.8% fully-supervised performance under AL, 88.5% under ASFDA, and 94.4% under ADA. We envision that Annotator will offer a simple, general, and efficient solution for label-efficient 3D applications.

POSTER-238: Mechanic: A Learning Rate Tuner

Keywords: optimization deep learning online convex optimization

Scores: [ 7 6 7 6 ]

We introduce a technique for tuning the learning rate scale factor of any base optimization algorithm and schedule automatically, which we call Mechanic. Our method provides a practical realization of recent theoretical reductions for accomplishing a similar goal in online convex optimization. We rigorously evaluate Mechanic on a range of large scale deep learning tasks with varying batch sizes, schedules, and base optimization algorithms. These experiments demonstrate that depending on the problem, Mechanic either comes very close to, matches or even improves upon manual tuning of learning rates.

SPOTLIGHT-35: HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

Keywords: genomics hyena foundation models large language models transformers

Scores: [ 7 7 7 8 7 ]

Genomic (DNA) sequences encode an enormous amount of information for gene regulation and protein synthesis. Similar to natural language models, researchers have proposed foundation models in genomics to learn generalizable features from unlabeled genome data that can then be fine-tuned for downstream tasks such as identifying regulatory elements. Due to the quadratic scaling of attention, previous Transformer-based genomic models have used 512 to 4k tokens as context (<0.001% of the human genome), significantly limiting the modeling of long-range interactions in DNA. In addition, these methods rely on tokenizers or fixed k-mers to aggregate meaningful DNA units, losing single nucleotide resolution (i.e. DNA "characters") where subtle genetic variations can completely alter protein function via single nucleotide polymorphisms (SNPs). Recently, Hyena, a large language model based on implicit convolutions was shown to match attention in quality while allowing longer context lengths and lower time complexity. Leveraging Hyena’s new long-range capabilities, we present HyenaDNA, a genomic foundation model pretrained on the human reference genome with context lengths of up to 1 million tokens at the single nucleotide-level – an up to 500x increase over previous dense attention-based models. HyenaDNA scales sub-quadratically in sequence length (training up to 160x faster than Transformer), uses single nucleotide tokens, and has full global context at each layer. We explore what longer context enables - including the first use of in-context learning in genomics for simple adaptation to novel tasks without updating pretrained model weights. On fine-tuned benchmarks from the Nucleotide Transformer, HyenaDNA reaches state-of-the-art (SotA) on 12 of 18 datasets using a model with orders of magnitude less parameters and pretraining data.1 On the GenomicBenchmarks, HyenaDNA surpasses SotA on 7 of 8 datasets on average by +10 accuracy points. Code at

POSTER-239: Uncovering Meanings of Embeddings via Partial Orthogonality

Keywords: embedding representation graphical models partial orthogonality Markov boundary

Scores: [ 6 4 2 6 ]

Machine learning tools often rely on embedding text as vectors of real numbers.In this paper, we study how the semantic structure of language is encoded in the algebraic structure of such embeddings.Specifically, we look at a notion of "semantic independence" capturing the idea that, e.g., "eggplant" and "tomato" are independent given "vegetable". Although such examples are intuitive, it is difficult to formalize such a notion of semantic independence. The key observation here is that any sensible formalization should obey a set of so-called independence axioms, and thus any algebraic encoding of this structure should also obey these axioms. This leads us naturally to use partial orthogonality as the relevant algebraic structure. We develop theory and methods that allow us to demonstrate that partial orthogonality does indeed capture semantic independence.Complementary to this, we also introduce the concept of independence preserving embeddings where embeddings preserve the conditional independence structures of a distribution, and we prove the existence of such embeddings and approximations to them.

POSTER-240: SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Keywords: Text-to-Image Diffusion model mobile devices distillation

Scores: [ 5 7 7 8 ]

Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of denoising iterations, making them computationally expensive and slow to run. As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale. This is costly and has privacy implications, especially when user data is sent to a third party. To overcome these challenges, we present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in less than 2 seconds. We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation. Further, we enhance the step distillation by exploring training strategies and introducing regularization from classifier-free guidance. Our extensive experiments on MS-COCO show that our model with \(8\) denoising steps achieves better FID and CLIP scores than Stable Diffusion v$1.5$ with \(50\) steps. Our work democratizes content creation by bringing powerful text-to-image diffusion models to the hands of users.

POSTER-241: Domain Agnostic Fourier Neural Operators

Keywords: Operator-Regression Neural Networks Neural Operators Data-Driven Physics Modeling Geometrical and Topological Shape Changes

Scores: [ 5 6 6 7 6 ]

POSTER-242: Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness

Keywords: mutli-armed bandits bandits with knapsacks primal-dual approaches

Scores: [ 4 7 6 6 ]

We consider contextual bandit problems with knapsacks [CBwK], a problem where at each round, a scalar reward is obtained and vector-valued costs are suffered. The learner aims to maximize the cumulative rewards while ensuring that the cumulative costs are lower than some predetermined cost constraints. We assume that contexts come from a continuous set, that costs can be signed, and that the expected reward and cost functions, while unknown, may be uniformly estimated---a typical assumption in the literature. In this setting, total cost constraints had so far to be at least of order \(T^{3/4}\), where \(T\) is the number of rounds, and were even typically assumed to depend linearly on \(T\). We are however motivated to use CBwK to impose a fairness constraint of equalized average costs between groups: the budget associated with the corresponding cost constraints should be as close as possible to the natural deviations, of order \(\sqrt{T}\). To that end, we introduce a dual strategy based on projected-gradient-descent updates, that is able to deal with total-cost constraints of the order of \(\sqrt{T}\) up to poly-logarithmic terms. This strategy is more direct and simpler than existing strategies in the literature. It relies on a careful, adaptive, tuning of the step size.

POSTER-243: CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

Keywords: Neural Radiance Field; Continual Learning; Scene Representation

Scores: [ 5 5 6 7 5 ]

Existing methods for adapting Neural Radiance Fields (NeRFs) to scene changes require extensive data capture and model retraining, which is both time-consuming and labor-intensive. In this paper, we tackle the challenge of efficiently adapting NeRFs to real-world scene changes over time using a few new images while retaining the memory of unaltered areas, focusing on the continual learning aspect of NeRFs. To this end, we propose CL-NeRF, which consists of two key components: a lightweight expert adaptor for adapting to new changes and evolving scene representations and a conflict-aware knowledge distillation learning objective for memorizing unchanged parts. We also present a new benchmark for evaluating Continual Learning of NeRFs with comprehensive metrics. Our extensive experiments demonstrate that CL-NeRF can synthesize high-quality novel views of both changed and unchanged regions with high training efficiency, surpassing existing methods in terms of reducing forgetting and adapting to changes. Code and benchmark will be made available.

POSTER-244: Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors

Keywords: 3D Reconstruction SDF Neural Rendering Implicit Representations SLAM

Scores: [ 5 6 7 5 ]

Learning neural implicit representations has achieved remarkable performance in 3D reconstruction from multi-view images. Current methods use volume rendering to render implicit representations into either RGB or depth images that are supervised by the multi-view ground truth. However, rendering a view each time suffers from incomplete depth at holes and unawareness of occluded structures from the depth supervision, which severely affects the accuracy of geometry inference via volume rendering. To resolve this issue, we propose to learn neural implicit representations from multi-view RGBD images through volume rendering with an attentive depth fusion prior. Our prior allows neural networks to sense coarse 3D structures from the Truncated Signed Distance Function (TSDF) fused from all available depth images for rendering. The TSDF enables accessing the missing depth at holes on one depth image and the occluded parts that are invisible from the current view. By introducing a novel attention mechanism, we allow neural networks to directly use the depth fusion prior with the inferred occupancy as the learned implicit function. Our attention mechanism works with either a one-time fused TSDF that represents a whole scene or an incrementally fused TSDF that represents a partial scene in the context of Simultaneous Localization and Mapping (SLAM). Our evaluations on widely used benchmarks including synthetic and real-world scans show our superiority over the latest neural implicit methods.

POSTER-245: Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift

Keywords: contrastive learning; self training; distribution shift; semi supervised learning; unsupervised domain adaptation

Scores: [ 6 6 7 7 ]

Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it is absent (semi-supervised learning). However, despite the popularity and compatibility of these techniques, their efficacy in combination remains surprisingly unexplored. In this paper, we first undertake a systematic empirical investigation of this combination, finding (i) that in domain adaptation settings, self-training and contrastive learning offer significant complementary gains; and (ii) that in semi-supervised learning settings, surprisingly, the benefits are not synergistic. Across eight distribution shift datasets (e.g., BREEDs, WILDS), we demonstrate that the combined method obtains 3--8% higher accuracy than either approach independently. Finally, we theoretically analyze these techniques in a simplified model of distribution shift demonstrating scenarios under which the features produced by contrastive learning can yield a good initialization for self-training to further amplify gains and achieve optimal performance, even when either method alone would fail.

POSTER-246: Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

Keywords: Alternating Gradient Descent Multimodal Mixture of Experts AGD MoE Deep Learning Optimization

Scores: [ 5 5 5 3 ]

We present Integrated Multimodal Perception (IMP), a simple and scalable multimodal multi-task training and modeling approach. IMP integrates multimodal inputs including image, video, text, and audio into a single Transformer encoder with minimal modality-specific components. IMP makes use of a novel design that combines Alternating Gradient Descent (AGD) and Mixture-of-Experts (MoE) for efficient model & task scaling. We conduct extensive empirical studies and reveal the following key insights: 1) performing gradient descent updates by alternating on diverse modalities, loss functions, and tasks, with varying input resolutions, efficiently improves the model. 2) sparsification with MoE on a single modality-agnostic encoder substantially improves the performance, outperforming dense models that use modality-specific encoders or additional fusion layers and greatly mitigating the conflicts between modalities. IMP achieves competitive performance on a wide range of downstream tasks including video classification, image classification, image-text, and video-text retrieval. Most notably, we train a sparse IMP-MoE-L focusing on video tasks that achieves new state-of-the-art in zero-shot video classification: 77.0% on Kinetics-400, 76.8% on Kinetics-600, and 68.3% on Kinetics-700, improving the previous state-of-the-art by +5%, +6.7%, and +5.8%, respectively, while using only 15% of their total training computational cost.

POSTER-247: Self-Supervised Reinforcement Learning that Transfers using Random Features

Keywords: deep reinforcement learning self-supervised learning

Scores: [ 5 5 7 7 4 ]

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across tasks. Model-based RL, on the other hand, learns task-agnostic models of the world that naturally enables transfer across different reward functions, but struggles to scale to complex environments due to the compounding error. To get the best of both worlds, we propose a self-supervised reinforcement learning method that enables the transfer of behaviors across tasks with different rewards, while circumventing the challenges of model-based RL. In particular, we show self-supervised pre-training of model-free reinforcement learning with a number of random features as rewards allows implicit modeling of long-horizon environment dynamics. Then, planning techniques like model-predictive control using these implicit models enable fast adaptation to problems with new reward functions. Our method is self-supervised in that it can be trained on offline datasets without reward labels, but can then be quickly deployed on new tasks. We validate that our proposed method enables transfer across tasks on a variety of manipulation and locomotion domains in simulation, opening the door to generalist decision-making agents.

POSTER-248: Sampling weights of deep neural networks

Keywords: random sampling neural network parameters iterative optimization

Scores: [ 6 6 4 6 6 6 ]

POSTER-249: A Logic for Expressing Log-Precision Transformers

Keywords: transformers logic reasoning circuit complexity mechanistic interpretability

Scores: [ 7 7 7 7 ]

One way to interpret the reasoning power of transformer-based language models is to describe the types of logical rules they can resolve over some input text. Recently, Chiang et al. (2023) showed that finite-precision transformer classifiers can be equivalently expressed in a generalization of first-order logic. However, finite-precision transformers are a weak transformer variant because, as we show, a single head can only attend to a constant number of tokens and, in particular, cannot represent uniform attention. Since attending broadly is a core capability for transformers, we ask whether a minimally more expressive model that can attend universally can also be characterized in logic. To this end, we analyze transformers whose forward pass is computed in \(\log n\) precision on contexts of length \(n\). We prove any log-precision transformer classifier can be equivalently expressed as a first-order logic sentence that, in addition to standard universal and existential quantifiers, may also contain majority-vote quantifiers. This is the tightest known upper bound and first logical characterization of log-precision transformers.

POSTER-250: Data Selection for Language Models via Importance Resampling

Keywords: Language models pretraining data selection fine-tuning

Scores: [ 6 8 8 4 4 ]

Selecting a suitable pretraining dataset is crucial for both general-domain (e.g., GPT-3) and domain-specific (e.g., Codex) language models (LMs). We formalize this problem as selecting a subset of a large raw unlabeled dataset to match a desired target distribution given unlabeled target samples. Due to the scale and dimensionality of the raw text data, existing methods use simple heuristics or require human experts to manually curate data. Instead, we extend the classic importance resampling approach used in low-dimensions for LM data selection. We propose Data Selection with Importance Resampling (DSIR), an efficient and scalable framework that estimates importance weights in a reduced feature space for tractability and selects data with importance resampling according to these weights. We instantiate the DSIR framework with hashed n-gram features for efficiency, enabling the selection of 100M documents from the full Pile dataset in 4.5 hours. To measure whether hashed n-gram features preserve the aspects of the data that are relevant to the target, we define KL reduction, a data metric that measures the proximity between the selected pretraining data and the target on some feature space. Across 8 data selection methods (including expert selection), KL reduction on hashed n-gram features highly correlates with average downstream accuracy (r=0.82). When selecting data for continued pretraining on a specific domain, DSIR performs comparably to expert curation across 8 target distributions. When pretraining general-domain models (target is Wikipedia and books), DSIR improves over random selection and heuristic filtering baselines by 2--2.5% on the GLUE benchmark.

POSTER-251: Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

Keywords: Learning from human preferences self-supervised learning exploration in reinforcement learning

Scores: [ 5 7 7 6 ]

Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision making tasks with a non-trivial element of exploration requires either specifying carefully designed reward functions or relying on indiscriminate, novelty seeking exploration bonuses. Human supervisors can provide effective guidance in the loop to direct the exploration process, but prior methods to leverage this guidance require constant synchronous high-quality human feedback, which is expensive and impractical to obtain. In this work, we propose a technique - Human Guided Exploration (HUGE), that is able to leverage low-quality feedback from non-expert users, which is infrequent, asynchronous and noisy, to guide exploration for reinforcement learning, without requiring careful reward specification. The key idea is to separate the challenges of directed exploration and policy learning - human feedback is used to direct exploration, while self-supervised policy learning is used to independently learn unbiased behaviors from the collected data. We show that this procedure can leverage noisy, asynchronous human feedback to learn tasks with no hand-crafted reward design or exploration bonuses. We show that HUGE is able to learn a variety of challenging multi-stage robotic navigation and manipulation tasks in simulation using crowdsourced feedback from non-expert users. Moreover, this paradigm can be scaled to learning directly on real-world robots.

POSTER-252: Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Keywords: Causal discovery Score matching Score-based generative modeling

Scores: [ 4 7 6 4 6 ]

This paper provides statistical sample complexity bounds for score-matching and its applications in causal discovery. We demonstrate that accurate estimation of the score function is achievable by training a standard deep ReLU neural network using stochastic gradient descent. We establish bounds on the error rate of recovering causal relationships using the score-matching-based causal discovery method of Rolland et al. [2022], assuming a sufficiently good estimation of the score function. Finally, we analyze the upper bound of score-matching estimation within the score-based generative modeling, which has been applied for causal discovery but is also of independent interest within the domain of generative models.

POSTER-253: Adaptive Linear Estimating Equations

Keywords: bandit algorithm statistical inference adaptively collected data asymptotic normality

Scores: [ 6 6 7 5 ]

Sequential data collection has emerged as a widely adopted technique for enhancing the efficiency of data gathering processes. Despite its advantages, such data collection mechanism often introduces complexities to the statistical inference procedure. For instance, the ordinary least squares (OLS) estimator in an adaptive linear regression model can exhibit non-normal asymptotic behavior, posing challenges for accurate inference and interpretation. In this paper, we propose a general method for constructing debiased estimator which remedies this issue. It makes use of the idea of adaptive linear estimating equations, and we establish theoretical guarantees of asymptotic normality, supplemented by discussions on achieving near-optimal asymptotic variance. A salient feature of our estimator is that in the context of multi-armed bandits, our estimator retains the non-asymptotic performance of the least squares estimator while obtaining asymptotic normality property. Consequently, this work helps connect two fruitful paradigms of adaptive inference: a) non-asymptotic inference using concentration inequalities and b) asymptotic inference via asymptotic normality.

POSTER-254: The Graph Pencil Method: Mapping Subgraph Densities to Stochastic Block Models

Keywords: Stochastic block model SBM graphons matrix pencil method method of moments

Scores: [ 6 5 6 ]

In this work, we describe a method that determines an exact map from a finite set of subgraph densities to the parameters of a stochastic block model (SBM) matching these densities. Given a number K of blocks, the subgraph densities of a finite number of stars and bistars uniquely determines a single element of the class of all degree-separated stochastic block models with K blocks. Our method makes it possible to translate estimates of these subgraph densities into model parameters, and hence to use subgraph densities directly for inference. The computational overhead is negligible; computing the translation map is polynomial in K, but independent of the graph size once the subgraph densities are given.

POSTER-255: Fair Allocation of Indivisible Chores: Beyond Additive Costs

Keywords: fair allocation of chores beyond additive cost functions bin packing job scheduling

Scores: [ 5 6 7 5 ]

We study the maximin share (MMS) fair allocation of \(m\) indivisible tasks to \(n\) agents who have costs for completing the assigned tasks.It is known that exact MMS fairness cannot be guaranteed, and so far the best-known approximation for additive cost functions is \(\frac{13}{11}\) by Huang and Segal-Halevi [EC, 2023]; however, beyond additivity, very little is known. In this work, we first prove that no algorithm can ensure better than \(\min\{n,\frac{\log m}{\log \log m}\}\)-approximation if the cost functions are submodular. This result also shows a sharp contrast with the allocation of goods where constant approximations exist as shown by Barman and Krishnamurthy [TEAC, 2020] and Ghodsi et al. [AIJ, 2022]. We then prove that for subadditive costs, there always exists an allocation that is \(\min\{n,\lceil\log m\rceil\}\)-approximation, and thus the approximation ratio is asymptotically tight.Besides multiplicative approximation, we also consider the ordinal relaxation, 1-out-of-\(d\) MMS, which was recently proposed by Hosseini et al. [JAIR and AAMAS, 2022]. Our impossibility result implies that for any \(d\ge 2\), a 1-out-of-\(d\) MMS allocation may not exist.Due to these hardness results for general subadditive costs, we turn to studying two specific subadditive costs, namely, bin packing and job scheduling. For both settings, we show that constant approximate allocations exist for both multiplicative and ordinal relaxations of MMS.

SPOTLIGHT-36: Exploring Geometry of Blind Spots in Vision models

Keywords: Neural networks Vision models blind spots undersensitivity invariance level set geometry input connectivity

Scores: [ 7 7 8 5 6 ]

Despite the remarkable success of deep neural networks in a myriad of settings, several works have demonstrated their overwhelming sensitivity to near-imperceptible perturbations, known as adversarial attacks. On the other hand, prior works have also observed that deep networks can be under-sensitive, wherein large-magnitude perturbations in input space do not induce appreciable changes to network activations. In this work, we study in detail the phenomenon of under-sensitivity in vision models such as CNNs and Transformers, and present techniques to study the geometry and extent of “equi-confidence” level sets of such networks. We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space using orthogonal components of the local gradients. Given a source image, we use this algorithm to identify inputs that lie in the same equi-confidence level set as the source image despite being perceptually similar to arbitrary images from other classes. We further observe that the source image is linearly connected by a high-confidence path to these inputs, uncovering a star-like structure for level sets of deep networks. Furthermore, we attempt to identify and estimate the extent of these connected higher-dimensional regions over which the model maintains a high degree of confidence.

POSTER-256: FairLISA: Fair User Modeling with Limited Sensitive Attributes Information

Keywords: fairness user modeling

Scores: [ 7 8 5 6 4 ]

POSTER-257: Focus Your Attention when Few-Shot Classification

Keywords: few-shot image classification fine-tuning vision transformers

Scores: [ 5 4 5 5 5 ]

POSTER-258: Static and Sequential Malicious Attacks in the Context of Selective Forgetting

Keywords: Selective forgetting static setting sequential setting security and robustness

Scores: [ 4 6 5 7 ]

With the growing demand for the right to be forgotten, there is an increasing need for machine learning models to forget sensitive data and its impact. To address this, the paradigm of selective forgetting (a.k.a machine unlearning) has been extensively studied, which aims to remove the impact of requested data from a well-trained model without retraining from scratch. Despite its significant success, limited attention has been given to the security vulnerabilities of the unlearning system concerning malicious data update requests. Motivated by this, in this paper, we explore the possibility and feasibility of malicious data update requests during the unlearning process. Specifically, we first propose a new class of malicious selective forgetting attacks, which involves a static scenario where all the malicious data update requests are provided by the adversary at once. Additionally, considering the sequential setting where the data update requests arrive sequentially, we also design a novel framework for sequential forgetting attacks, which is formulated as a stochastic optimal control problem. We also propose novel optimization algorithms that can find the effective malicious data update requests. We perform theoretical analyses for the proposed selective forgetting attacks, and extensive experimental results validate the effectiveness of our proposed selective forgetting attacks. The source code is available in the supplementary material.

POSTER-259: Efficient Robust Bayesian Optimization for Arbitrary Uncertain inputs

Keywords: bayesian optimization robust optimization

Scores: [ 5 5 6 6 ]

Bayesian Optimization (BO) is a sample-efficient optimization algorithm widely employed across various applications. In some challenging BO tasks, input uncertainty arises due to the inevitable randomness in the optimization process, such as machining errors, execution noise, or contextual variability. This uncertainty deviates the input from the intended value before evaluation, resulting in significant performance fluctuations in the final result. In this paper, we introduce a novel robust Bayesian Optimization algorithm, AIRBO, which can effectively identify a robust optimum that performs consistently well under arbitrary input uncertainty. Our method directly models the uncertain inputs of arbitrary distributions by empowering the Gaussian Process with the Maximum Mean Discrepancy (MMD) and further accelerates the posterior inference via Nystrom approximation. Rigorous theoretical regret bound is established under MMD estimation error and extensive experiments on synthetic functions and real problems demonstrate that our approach can handle various input uncertainties and achieve a state-of-the-art performance.

POSTER-260: (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability

Keywords: SGD GD implicit bias large stepsizes edge of stability diagonal linear networks

Scores: [ 6 7 6 5 6 ]

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over \(2\)-layer diagonal linear networks. We prove the convergence of GD and SGD with macroscopic stepsizes in an overparametrised regression setting and characterise their solutions through an implicit regularisation problem. Our crisp characterisation leads to qualitative insights about the impact of stochasticity and stepsizes on the recovered solution. Specifically, we show that large stepsizes consistently benefit SGD for sparse regression problems, while they can hinder the recovery of sparse solutions for GD. These effects are magnified for stepsizes in a tight window just below the divergence threshold, in the ``edge of stability'' regime. Our findings are supported by experimental results.

POSTER-261: ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints

Keywords: offline RL support constraints heteroskedastic data

Scores: [ 5 6 6 5 ]

Offline reinforcement learning (RL) learns policies entirely from static datasets. Practical applications of offline RL will inevitably require learning from datasets where the variability of demonstrated behaviors changes non-uniformly across the state space. For example, at a red light, nearly all human drivers behave similarly by stopping, but when merging onto a highway, some drivers merge quickly, efficiently, and safely, while many hesitate or merge dangerously. Both theoretically and empirically, we show that typical offline RL methods, which are based on distribution constraints fail to learn from data with such non-uniform variability, due to the requirement to stay close to the behavior policy to the same extent across the state space. Ideally, the learned policy should be free to choose per state how closely to follow the behavior policy to maximize long-term return, as long as the learned policy stays within the support of the behavior policy. To instantiate this principle, we reweight the data distribution in conservative Q-learning (CQL) to obtain an approximate support constraint formulation. The reweighted distribution is a mixture of the current policy and an additional policy trained to mine poor actions that are likely under the behavior policy. Our method, CQL (ReDS), is theoretically motivated, and improves performance across a wide range of offline RL problems in games, navigation, and pixel-based manipulation.

POSTER-262: Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

Keywords: differential privacy in-context learning trustworthy ML

Scores: [ 6 7 7 5 5 ]

Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective membership inference attack against the data used to prompt LLMs. To address this vulnerability, one could forego prompting and resort to fine-tuning LLMs with known algorithms for private gradient descent. However, this comes at the expense of the practicality and efficiency offered by prompting. Therefore, we propose to privately learn to prompt. We first show that soft prompts can be obtained privately through gradient descent on downstream data. However, this is not the case for discrete prompts. Thus, we orchestrate a noisy vote among an ensemble of LLMs presented with different prompts, i.e., a flock of stochastic parrots. The vote privately transfers the flock's knowledge into a single public prompt. We show that LLMs prompted with our private algorithms closely match the non-private baselines. For example, using GPT3 as the base model, we achieve a downstream accuracy of 92.7% on the sst2 dataset with \((\varepsilon=0.147, \delta=10^{-6})\)-differential privacy vs. 95.2% for the non-private baseline. Through our experiments, we also show that our prompt-based approach is easily deployed with existing commercial~APIs.

SPOTLIGHT-37: Real-World Image Variation by Aligning Diffusion Inversion Chain

Keywords: image variation diffusion model image generation text-driven image editing

Scores: [ 7 5 7 7 6 ]

Recent diffusion model advancements have enabled high-fidelity images to be generated using text prompts. However, a domain gap exists between generated images and real-world images, which poses a challenge in generating high-quality variations of real-world images. Our investigation uncovers that this domain gap originates from a latents' distribution gap in different diffusion processes. To address this issue, we propose a novel inference pipeline called Real-world Image Variation by ALignment (RIVAL) that utilizes diffusion models to generate image variations from a single image exemplar. Our pipeline enhances the generation quality of image variations by aligning the image generation process to the source image's inversion chain. Specifically, we demonstrate that step-wise latent distribution alignment is essential for generating high-quality variations. To attain this, we design a cross-image self-attention injection for feature interaction and a step-wise distribution normalization to align the latent features. Incorporating these alignment processes into a diffusion model allows RIVAL to generate high-quality image variations without further parameter optimization. Our experimental results demonstrate that our proposed approach outperforms existing methods concerning semantic similarity and perceptual quality. This generalized inference pipeline can be easily applied to other diffusion-based generation tasks, such as image-conditioned text-to-image generation and stylization. Project page:

POSTER-263: MADG: Margin-based Adversarial Learning for Domain Generalization

Keywords: Domain Generalization Margin Loss Adversarial Learning Domain Adaptation

Scores: [ 5 6 6 5 5 ]

POSTER-264: Graph Denoising Diffusion for Inverse Protein Folding

Keywords: inverse folding graph neural networks roto-translation equivariance diffusion model

Scores: [ 6 5 6 7 ]

SPOTLIGHT-38: Uncovering motifs of concurrent signaling across multiple neuronal populations

Keywords: neuroscience multi-population neural recordings dimensionality reduction latent variable models Gaussian processes

Scores: [ 7 8 7 7 ]

POSTER-265: Robust Data Valuation with Weighted Banzhaf Values

Keywords: data valuation robustness weighted Banzhaf values

Scores: [ 6 6 6 6 ]

Data valuation, a principled way to rank the importance of each training datum, has become increasingly important. However, existing value-based approaches (e.g., Shapley) are known to suffer from the stochasticity inherent in utility functions that render consistent and reliable ranking difficult. Recently, Wang and Jia (2023) proposed the noise-structure-agnostic framework to advocate the Banzhaf value for its robustness against such stochasticity as it achieves the largest safe margin among many alternatives. Surprisingly, our empirical study shows that the Banzhaf value is not always the most robust when compared with a broader family: weighted Banzhaf values. To analyze this scenario, we introduce the concept of Kronecker noise to parameterize stochasticity, through which we prove that the uniquely robust semi-value, which can be analytically derived from the underlying Kronecker noise, lies in the family of weighted Banzhaf values while minimizing the worst-case entropy. In addition, we adopt the maximum sample reuse principle to design an estimator to efficiently approximate weighted Banzhaf values, and show that it enjoys the best time complexity in terms of achieving an \((\epsilon, \delta)\)-approximation. Our theory is verified under both synthetic and authentic noises. For the latter, we fit a Kronecker noise to the inherent stochasticity, which is then plugged in to generate the predicted most robust semi-value. Our study suggests that weighted Banzhaf values are promising when facing undue noises in data valuation.

POSTER-266: PlanE: Representation Learning over Planar Graphs

Keywords: Graph Representation Learning; Planar Graphs; Graph Property Prediction

Scores: [ 6 4 6 6 6 ]

Graph neural networks are prominent models for representation learning over graphs, where the idea is to iteratively compute representations of nodes of an input graph through a series of transformations in such a way that the learned graph function is isomorphism-invariant on graphs, which makes the learned representations graph invariants. On the other hand, it is well-known that graph invariants learned by these class of models are incomplete: there are pairs of non-isomorphic graphs which cannot be distinguished by standard graph neural networks. This is unsurprising given the computational difficulty of graph isomorphism testing on general graphs, but the situation begs to differ for special graph classes, for which efficient graph isomorphism testing algorithms are known, such as planar graphs. The goal of this work is to design architectures for efficiently learning complete invariants of planar graphs. Inspired by the classical planar graph isomorphism algorithm of Hopcroft and Tarjan, we propose PlanE as a framework for planar representation learning. PlanE includes architectures which can learn complete invariants over planar graphs while remaining practically scalable. We empirically validate the strong performance of the resulting model architectures on well-known planar graph benchmarks, achieving multiple state-of-the-art results.

POSTER-267: Knowledge Distillation Performs Partial Variance Reduction

Keywords: knowledge distillation stochastic optimization variance reduction

Scores: [ 7 6 6 7 ]

POSTER-268: GEX: A flexible method for approximating influence via Geometric Ensemble

Keywords: Influence Function Geometric Ensemble Loss Landscape

Scores: [ 7 7 5 6 6 ]

Through a deeper understanding of predictions of neural networks, Influence Function (IF) has been applied to various tasks such as detecting and relabeling mislabeled samples, dataset pruning, and separation of data sources in practice. However, we found standard approximations of IF suffer from performance degradation due to oversimplified influence distributions caused by their bilinear approximation, suppressing the expressive power of samples with a relatively strong influence. To address this issue, we propose a new interpretation of existing IF approximations as an average relationship between two linearized losses over parameters sampled from the Laplace approximation (LA). In doing so, we highlight two significant limitations of current IF approximations: the linearity of gradients and the singularity of Hessian. Accordingly, by improving each point, we introduce a new IF approximation method with the following features: i) the removal of linearization to alleviate the bilinear constraint and ii) the utilization of Geometric Ensemble (GE) tailored for non-linear losses. Empirically, our approach outperforms existing IF approximations for downstream tasks with lighter computation, thereby providing new feasibility of low-complexity/nonlinear-based IF design.

POSTER-269: InstanT: Semi-supervised Learning with Instance-dependent Thresholds

Keywords: semi-supervised learning pseudo-labeling

Scores: [ 7 5 7 6 5 ]

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves assigning pseudo-labels to confident unlabeled instances and incorporating them into the training set. Therefore, the selection criteria of confident instances are crucial to the success of SSL. Recently, there has been growing interest in the development of SSL methods that use dynamic or adaptive thresholds. Yet, these methods typically apply the same threshold to all samples, or use class-dependent thresholds for instances belonging to a certain class, while neglecting instance-level information. In this paper, we propose the study of instance-dependent thresholds, which has the highest degree of freedom compared with existing methods. Specifically, we devise a novel instance-dependent threshold function for all unlabeled instances by utilizing their instance-level ambiguity and the instance-dependent error rates of pseudo-labels, so instances that are more likely to have incorrect pseudo-labels will have higher thresholds. Furthermore, we demonstrate that our instance-dependent threshold function provides a bounded probabilistic guarantee for the correctness of the pseudo-labels it assigns.

POSTER-270: Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense

Keywords: federated learning backdoor learning robust federated aggregation data divergence

Scores: [ 7 5 5 5 5 ]

Federated learning algorithms enable neural network models to be trained across multiple decentralized edge devices without sharing private data. However, they are susceptible to backdoor attacks launched by malicious clients. Existing robust federated aggregation algorithms heuristically detect and exclude suspicious clients based on their parameter distances, but they are ineffective on Natural Language Processing (NLP) tasks. The main reason is that, although text backdoor patterns are obvious at the underlying dataset level, they are usually hidden at the parameter level, since injecting backdoors into texts with discrete feature space has less impact on the statistics of the model parameters. To settle this issue, we propose to identify backdoor clients by explicitly modeling the data divergence among clients in federated NLP systems. Through theoretical analysis, we derive the f-divergence indicator to estimate the client data divergence with aggregation updates and Hessians. Furthermore, we devise a dataset synthesization method with a Hessian reassignment mechanism guided by the diffusion theory to address the key challenge of inaccessible datasets in calculating clients' data Hessians.We then present the novel Federated F-Divergence-Based Aggregation~(\textbf{Fed-FA}) algorithm, which leverages the f-divergence indicator to detect and discard suspicious clients. Extensive empirical results show that Fed-FA outperforms all the parameter distance-based methods in defending against backdoor attacks among various natural language backdoor attack scenarios.

POSTER-271: DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

Keywords: speech representation learning self-supervised learning self-distillation discrete representation learning

Scores: [ 7 7 5 7 7 6 ]

In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering. We show that these concepts complement each other and result in a strong representation learning model for speech. DinoSR first extracts contextualized embeddings from the input audio with a teacher network, then runs an online clustering system on the embeddings to yield a machine-discovered phone inventory, and finally uses the discretized tokens to guide a student network. We show that DinoSR surpasses previous state-of-the-art performance in several downstream tasks, and provide a detailed analysis of the model and the learned discrete units.

POSTER-272: The Bayesian Stability Zoo

Keywords: Algorithmic stability Replicability Differential Privacy KL Stability Mutual Information Stability Global Stability Perfect Generalization PAC Learning Littlestone Dimension Clique Dimension PAC Bayes

Scores: [ 5 8 5 5 7 ]

We show that many definitions of stability found in the learning theory literature are equivalent to one another. We distinguish between two families of definitions of stability: distribution-dependent and distribution-independent Bayesian stability. Within each family, we establish equivalences between various definitions, encompassing approximate differential privacy, pure differential privacy, replicability, global stability, perfect generalization, TV stability, mutual information stability, KL-divergence stability, and Rényi-divergence stability. Along the way, we prove boosting results that enable the amplification of the stability of a learning rule. This work is a step towards a more systematic taxonomy of stability notions in learning theory, which can promote clarity and an improved understanding of an array of stability concepts that have emerged in recent years.

POSTER-273: Secure Out-of-Distribution Task Generalization with Energy-Based Models

Keywords: meta-generalization out-of-distribution tasks

Scores: [ 6 5 7 7 5 ]

The success of meta-learning on out-of-distribution (OOD) tasks in the wild has proved to be hit-and-miss.To safeguard the generalization capability of the meta-learned prior knowledge to OOD tasks, in particularly safety-critical applications, necessitates detection of an OOD task followed by adaptation of the task towards the prior. Nonetheless, the reliability of estimated uncertainty on OOD tasks by existing Bayesian meta-learning methods is restricted by incomplete coverage of the feature distribution shift and insufficient expressiveness of the meta-learned prior. Besides, they struggle to adapt an OOD task, running parallel to the line of cross-domain task adaptation solutions which are vulnerable to overfitting.To this end, we build a single coherent framework that supports both detection and adaptation of OOD tasks, while remaining compatible with off-the-shelf meta-learning backbones. The proposed Energy-Based Meta-Learning (EBML) framework learns to characterize any arbitrary meta-training task distribution with the composition of two expressive neural-network-based energy functions. We deploy the sum of the two energy functions, being proportional to the joint distribution of a task, as a reliable score for detecting OOD tasks; during meta-testing, we adapt the OOD task to in-distribution tasks by energy minimization.Experiments on four regression and classification datasets demonstrate the effectiveness of our proposal.

POSTER-274: Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning

Keywords: Physical Audiovisual;Commonsense Reasoning

Scores: [ 5 8 5 5 4 ]

In this paper, we propose a Disentangled Counterfactual Learning (DCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects’ physics commonsense based on both video and audio input, with the main challenge is how to imitate the reasoning ability of humans. Most of the current methods fail to take full advantage of different characteristics in multi-modal data, and lacking causal reasoning ability in models impedes the progress of implicit physical knowledge inferring. To address these issues, our proposed DCL method decouples videos into static (time-invariant) and dynamic (time-varying) factors in the latent space by the disentangled sequential encoder, which adopts a variational autoencoder (VAE) to maximize the mutual information with a contrastive loss function. Furthermore, we introduce a counterfactual learning module to augment the model’s reasoning ability by modeling physical knowledge relationships among different objects under counterfactual intervention. Our proposed method is a plug-and-play module that can be incorporated into any baseline. In experiments, we show that our proposed method improves baseline methods and achieves state-of-the-art performance. Our source code is available at

POSTER-275: NetHack is Hard to Hack

Keywords: imitation learning NetHack

Scores: [ 6 7 7 7 6 ]

POSTER-276: Derandomized novelty detection with FDR control via conformal e-values

Keywords: Conformal inference Derandomization E-values False discovery rate Out-of-distribution testing Testing for outliers Uncertainty

Scores: [ 6 5 7 7 ]

Conformal inference provides a general distribution-free method to rigorously calibrate the output of any machine learning algorithm for novelty detection. While this approach has many strengths, it has the limitation of being randomized, in the sense that it may lead to different results when analyzing twice the same data and this can hinder the interpretation of any findings. We propose to make conformal inferences more stable by leveraging suitable conformal e-values instead of p-values to quantify statistical significance. This solution allows the evidence gathered from multiple analyses of the same data to be aggregated effectively while provably controlling the false discovery rate. Further, we show that the proposed method can reduce randomness without much loss of power compared to standard conformal inference, partly thanks to an innovative way of weighting conformal e-values based on additional side information carefully extracted from the same data. Simulations with synthetic and real data confirm this solution can be effective at eliminating random noise in the inferences obtained with state-of-the-art alternative techniques, sometimes also leading to higher power.

POSTER-277: SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations

Keywords: Imitation learning Preference-based learning Safe imitation learning

Scores: [ 6 5 5 7 ]

We consider offline safe imitation learning (IL), where the agent aims to learn the safe policy that mimics preferred behavior while avoiding non-preferred behavior from non-preferred demonstrations and unlabeled demonstrations. This problem setting corresponds to various real-world scenarios, where satisfying safety constraints is more important than maximizing the expected return. However, it is very challenging to learn the policy to avoid constraint-violating (i.e. non-preferred) behavior, as opposed to standard imitation learning which learns the policy to mimic given demonstrations. In this paper, we present a hyperparameter-free offline safe IL algorithm, SafeDICE, that learns safe policy by leveraging the non-preferred demonstrations in the space of stationary distributions. Our algorithm directly estimates the stationary distribution corrections of the policy that imitate the demonstrations excluding the non-preferred behavior. In the experiments, we demonstrate that our algorithm learns a more safe policy that satisfies the cost constraint without degrading the reward performance, compared to baseline algorithms.

POSTER-278: Dream the Impossible: Outlier Imagination with Diffusion Models

Keywords: Outlier imagination machine learning

Scores: [ 5 6 7 7 5 ]

Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor intensity in data collection and cleaning, automating outlier data generation has been a long-desired alternative. Despite the appeal, generating photo-realistic outliers in the high dimensional pixel space has been an open challenge for the field. To tackle the problem, this paper proposes a new framework Dream-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the in-distribution (ID) data and classes. Specifically, Dream-OOD learns a text-conditioned latent space based on ID data, and then samples outliers in the low-likelihood region via the latent, which can be decoded into images by the diffusion model. Different from prior works [16, 95], Dream-OOD enables visualizing and understanding the imagined outliers, directly in the pixel space. We conduct comprehensive quantitative and qualitative studies to understand the efficacy of Dream-OOD, and show that training with the samples generated by Dream-OOD can significantly benefit OOD detection performance.

POSTER-279: Add and Thin: Diffusion for Temporal Point Processes

Keywords: Point Processes Diffusion Temporal Data Generative Model Forecasting Density Estimation Denoising

Scores: [ 7 6 5 7 ]

Autoregressive neural networks within the temporal point process (TPP) framework have become the standard for modeling continuous-time event data. Even though these models can expressively capture event sequences in a one-step-ahead fashion, they are inherently limited for long-term forecasting applications due to the accumulation of errors caused by their sequential nature. To overcome these limitations, we derive ADD-THIN, a principled probabilistic denoising diffusion model for TPPs that operates on entire event sequences. Unlike existing diffusion approaches, ADD-THIN naturally handles data with discrete and continuous components. In experiments on synthetic and real-world datasets, our model matches the state-of-the-art TPP models in density estimation and strongly outperforms them in forecasting.

POSTER-280: SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning

Keywords: Federated Learning Contribution Evaluation Shapley Value Knowledge Amalgamation

Scores: [ 6 5 4 5 6 ]

The evaluation of participant contribution in federated learning (FL) has recently gained significant attention due to its applicability in various domains, such as incentive mechanisms, robustness enhancement, and client selection. Previous approaches have predominantly relied on the widely adopted Shapley value for participant evaluation. However, the computation of the Shapley value is expensive, despite using techniques like gradient-based model reconstruction and truncating unnecessary evaluations. Therefore, we present an efficient approach called Single-round Participants Amalgamation for Contribution Evaluation (SPACE). SPACE incorporates two novel components, namely Federated Knowledge Amalgamation and Prototype-based Model Evaluation to reduce the evaluation effort by eliminating the dependence on the size of the validation set and enabling participant evaluation within a single communication round. Experimental results demonstrate that SPACE outperforms state-of-the-art methods in terms of both running time and Pearson’s Correlation Coefficient (PCC). Furthermore, extensive experiments conducted on applications, client reweighting, and client selection highlight the effectiveness of SPACE. The code is available at

POSTER-281: Exponential Lower Bounds for Fictitious Play in Potential Games

Keywords: fictitious play convergence rate potential games

Scores: [ 7 7 7 7 ]

Fictitious Play (FP) is a simple and natural dynamic for repeated play with many applications in game theory and multi-agent reinforcement learning. It was introduced by Brown and its convergence properties for two-player zero-sum games was established later by Robinson. Potential games [Monderer and Shapley 1996] is another class of games which exhibit the FP property [Monderer and Shapley 1996], i.e., FP dynamics converges to a Nash equilibrium if all agents follows it. Nevertheless, except for two-player zero-sum games and for specific instances of payoff matrices [Abernethy et. al. 2021] or for adversarial tie-breaking rules [Daskalakis and Pan, 2014], the \textit{convergence rate} of FP is unknown. In this work, we focus on the rate of convergence of FP when applied to potential games and more specifically identical payoff games. We prove that FP can take exponential time (in the number of strategies) to reach a Nash equilibrium, even if the game is restricted to \textit{two agents}. To prove this, we recursively construct a two-player coordination game with a unique Nash equilibrium. Moreover, every approximate Nash equilibrium in the constructed game must be close to the pure Nash equilibrium in \(\ell_1\)-distance.

POSTER-282: Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond

Keywords: mean-field regime feature learning Neural network optimization sparse parity function classification sample complexity

Scores: [ 6 6 6 6 ]

Neural network in the mean-field regime is known to be capable of \textit{feature learning}, unlike the kernel (NTK) counterpart. Recent works have shown that mean-field neural networks can be globally optimized by a noisy gradient descent update termed the \textit{mean-field Langevin dynamics} (MFLD). However, all existing guarantees for MFLD only considered the \textit{optimization} efficiency, and it is unclear if this algorithm leads to improved \textit{generalization} performance and sample complexity due to the presence of feature learning. To fill this gap, in this work we study the statistical and computational complexity of MFLD in learning a class of binary classification problems. Unlike existing margin bounds for neural networks, we avoid the typical norm control by utilizing the perspective that MFLD optimizes the \textit{distribution} of parameters rather than the parameter itself; this leads to an improved analysis of the sample complexity and convergence rate. We apply our general framework to the learning of \(k\)-sparse parity functions, where we prove that unlike kernel methods, two-layer neural networks optimized by MFLD achieves a sample complexity where the degree \(k\) is ``decoupled'' from the exponent in the dimension dependence.

POSTER-283: No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models

Keywords: language models transformers efficient training

Scores: [ 6 6 7 6 5 ]

The computation necessary for training Transformer-based language models has skyrocketed in recent years.This trend has motivated research on efficient training algorithms designed to improve training, validation, and downstream performance faster than standard training. In this work, we revisit three categories of such algorithms: dynamic architectures (layer stacking, layer dropping), batch selection (selective backprop., RHO-loss), and efficient optimizers (Lion, Sophia). When pre-training BERT and T5 with a fixed computation budget using such methods, we find that their training, validation, and downstream gains vanish compared to a baseline with a fully-decayed learning rate. We define an evaluation protocol that enables computation to be done on arbitrary machines by mapping all computation time to a reference machine which we call reference system time. We discuss the limitations of our proposed protocol and release our code to encourage rigorous research in efficient training procedures:

POSTER-284: GlyphControl: Glyph Conditional Control for Visual Text Generation

Keywords: Generative Models Visual Text Generation Diffusion Models

Scores: [ 7 6 6 4 4 ]

Recently, there has been an increasing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called GlyphControl to address this task. Unlike existing methods that rely on character-aware text encoders like ByT5 and require retraining of text-to-image models, our approach leverages additional glyph conditional information to enhance the performance of the off-the-shelf Stable-Diffusion model in generating accurate visual text. By incorporating glyph instructions, users can customize the content, location, and size of the generated text according to their specific requirements. To facilitate further research in visual text generation, we construct a training benchmark dataset called LAION-Glyph. We evaluate the effectiveness of our approach by measuring OCR-based metrics, CLIP score, and FID of the generated visual text. Our empirical evaluations demonstrate that GlyphControl outperforms the recent DeepFloyd IF approach in terms of OCR accuracy, CLIP score, and FID, highlighting the efficacy of our method.

SPOTLIGHT-39: Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Keywords: neural decoding brain-computer interfaces spike sorting variational inference generative models

Scores: [ 8 8 4 7 ]

Neural decoding and its applications to brain computer interfaces (BCI) are essential for understanding the association between neural activity and behavior. A prerequisite for many decoding approaches is spike sorting, the assignment of action potentials (spikes) to individual neurons. Current spike sorting algorithms, however, can be inaccurate and do not properly model uncertainty of spike assignments, therefore discarding information that could potentially improve decoding performance. Recent advances in high-density probes (e.g., Neuropixels) and computational methods now allow for extracting a rich set of spike features from unsorted data; these features can in turn be used to directly decode behavioral correlates. To this end, we propose a spike sorting-free decoding method that directly models the distribution of extracted spike features using a mixture of Gaussians (MoG) encoding the uncertainty of spike assignments, without aiming to solve the spike clustering problem explicitly. We allow the mixing proportion of the MoG to change over time in response to the behavior and develop variational inference methods to fit the resulting model and to perform decoding. We benchmark our method with an extensive suite of recordings from different animals and probe geometries, demonstrating that our proposed decoder can consistently outperform current methods based on thresholding (i.e. multi-unit activity) and spike sorting. Open source code is available at

POSTER-285: SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models

Keywords: Large Language Model; Task Planning; Embodied AI; Robotics; Software Automation; Decision making

Scores: [ 6 4 6 7 ]

Computer end users have spent billions of hours completing daily tasks like tabular data processing and project timeline scheduling. Most of these tasks are repetitive and error-prone, yet most end users lack the skill to automate these burdensome works. With the advent of large language models (LLMs), directing software with natural language user requests become a reachable goal. In this work, we propose a SheetCopilot agent that takes natural language task and control spreadsheet to fulfill the requirements. We propose a set of atomic actions as an abstraction of spreadsheet software functionalities. We further design a state machine-based task planning framework for LLMs to robustly interact with spreadsheets. We curate a representative dataset containing 221 spreadsheet control tasks and establish a fully automated evaluation pipeline for rigorously benchmarking the ability of LLMs in software control tasks. Our SheetCopilot correctly completes 44.3% of tasks for a single generation, outperforming the strong code generation baseline by a wide margin. Our project page:

SPOTLIGHT-40: Stable Diffusion is Unstable

Keywords: Adversarial Attack Generative Model Diffusion Model Latent Diffusion Model Conditional Latent Diffusion Model

Scores: [ 6 6 7 7 ]

Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifically, the introduction of small perturbations to the text prompts can result in the blending of primary subjects with other categories or their complete disappearance in the generated images. In this paper, we propose Auto-attack on Text-to-image Models (ATM), a gradient-based approach, to effectively and efficiently generate such perturbations. By learning a Gumbel Softmax distribution, we can make the discrete process of word replacement or extension continuous, thus ensuring the differentiability of the perturbation generation. Once the distribution is learned, ATM can sample multiple attack samples simultaneously. These attack samples can prevent the generative model from generating the desired subjects without tampering with the category keywords in the prompt. ATM has achieved a 91.1% success rate in short-text attacks and an 81.2% success rate in long-text attacks. Further empirical analysis revealed three attack patterns based on: 1) variability in generation speed, 2) similarity of coarse-grained characteristics, and 3) polysemy of words. The code is available at

POSTER-286: FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy

Keywords: natural language generation; evaluation metrics; cross-entropy; language model

Scores: [ 3 6 5 4 6 ]

Measuring the distance between machine-produced and human language is a critical open problem. Inspired by empirical findings from psycholinguistics on the periodicity of entropy in language, we propose FACE, a set of metrics based on Fourier Analysis of the estimated Cross-Entropy of language, for measuring the similarity between model-generated and human-written languages. Based on an open-ended generation task and the experimental data from previous studies, we find that FACE can effectively identify the human-model gap, scales with model size, reflects the outcomes of different sampling methods for decoding, correlates well with other evaluation metrics and with human judgment scores.

POSTER-287: CQM: Curriculum Reinforcement Learning with a Quantized World Model

Keywords: Reinforcement Learning Curriculum Learning Goal-conditioned RL

Scores: [ 6 7 8 5 5 ]

Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curriculum goals in a high-dimensional space. Thus, they usually rely on manually specified goal spaces. To alleviate this limitation and improve the scalability of the curriculum, we propose a novel curriculum method that automatically defines the semantic goal space which contains vital information for the curriculum process, and suggests curriculum goals over it. To define the semantic goal space, our method discretizes continuous observations via vector quantized-variational autoencoders (VQ-VAE) and restores the temporal relations between the discretized observations by a graph. Concurrently, ours suggests uncertainty and temporal distance-aware curriculum goals that converges to the final goals over the automatically composed goal space. We demonstrate that the proposed method allows efficient explorations in an uninformed environment with raw goal examples only. Also, ours outperforms the state-of-the-art curriculum RL methods on data efficiency and performance, in various goal-reaching tasks even with ego-centric visual inputs.

SPOTLIGHT-41: Tracr: Compiled Transformers as a Laboratory for Interpretability

Keywords: interpretability transformers language models RASP Tracr mechanistic interpretability

Scores: [ 6 8 7 7 ]

We show how to "compile" human-readable programs into standard decoder-only transformer models. Our compiler, Tracr, generates models with known structure. This structure can be used to design experiments. For example, we use it to study "superposition" in transformers that execute multi-step algorithms. Additionally, the known structure of Tracr-compiled models can serve as ground-truth for evaluating interpretability methods. Commonly, because the "programs" learned by transformers are unknown it is unclear whether an interpretation succeeded. We demonstrate our approach by implementing and examining programs including computing token frequencies, sorting, and parenthesis checking. We provide an open-source implementation of Tracr at

POSTER-288: Ignorance is Bliss: Robust Control via Information Gating

Keywords: representation learning mutual information

Scores: [ 5 6 7 6 6 ]

Informational parsimony provides a useful inductive bias for learning representations that achieve better generalization by being robust to noise and spurious correlations. We propose information gating as a way to learn parsimonious representations that identify the minimal information required for a task. When gating information, we can learn to reveal as little information as possible so that a task remains solvable, or hide as little information as possible so that a task becomes unsolvable. We gate information using a differentiable parameterization of the signal-to-noise ratio, which can be applied to arbitrary values in a network, e.g., erasing pixels at the input layer or activations in some intermediate layer. When gating at the input layer, our models learn which visual cues matter for a given task. When gating intermediate layers, our models learn which activations are needed for subsequent stages of computation. We call our approach InfoGating. We apply InfoGating to various objectives such as multi-step forward and inverse dynamics models, Q-learning, and behavior cloning, highlighting how InfoGating can naturally help in discarding information not relevant for control. Results show that learning to identify and use minimal information can improve generalization in downstream tasks. Policies based on InfoGating are considerably more robust to irrelevant visual features, leading to improved pretraining and finetuning of RL models.

POSTER-289: Language Semantic Graph Guided Data-Efficient Learning

Keywords: Data-Efficient Learning Language Semantic Graph

Scores: [ 6 4 6 7 4 ]

POSTER-290: ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

Keywords: Forecasting Zero-shot Synthetic Data

Scores: [ 6 5 5 5 ]

The vast majority of time-series forecasting approaches require a substantial training dataset. However, many real-life forecasting applications have very little initial observations, sometimes just 40 or fewer. Thus, the applicability of most forecasting methods is restricted in data-sparse commercial applications. While there is recent work in the setting of very limited initial data (so-called `zero-shot' forecasting), its performance is inconsistent depending on the data used for pretraining. In this work, we take a different approach and devise ForecastPFN, the first zero-shot forecasting model trained purely on a novel synthetic data distribution. ForecastPFN is a prior-data fitted network, trained to approximate Bayesian inference, which can make predictions on a new time series dataset in a single forward pass. Through extensive experiments, we show that zero-shot predictions made by ForecastPFN are more accurate and faster compared to state-of-the-art forecasting methods, even when the other methods are allowed to train on hundreds of additional in-distribution data points.

POSTER-291: Human-Guided Complexity-Controlled Abstractions

Keywords: human-in-the-loop representation learning interpretability

Scores: [ 6 6 5 5 ]

Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g., "bird" vs. "sparrow'") and use the appropriate abstraction based on tasks. Inspired by this, we train neural models to generate a spectrum of discrete representations, and control the complexity of the representations (roughly, how many bits are allocated for encoding inputs) by tuning the entropy of the distribution over representations. In finetuning experiments, using only a small number of labeled examples for a new task, we show that (1) tuning the representation to a task-appropriate complexity level supports the greatest finetuning performance, and (2) in a human-participant study, users were able to identify the appropriate complexity level for a downstream task via visualizations of discrete representations. Our results indicate a promising direction for rapid model finetuning by leveraging human insight.

POSTER-292: Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network

Keywords: motion perception optical flow estimation attention mechanism psychophysics In silico neurophysiology human vision

Scores: [ 7 7 8 6 6 ]

POSTER-293: D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts

Keywords: 3D reconstruction constructive solid geometry unsupervised learning compact shape assembly

Scores: [ 7 6 6 6 8 ]

We present D$^2$CSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) representations of 3D CAD shapes. Our network is trained to reconstruct a 3D shape by a fixed-order assembly of quadric primitives, with both branches producing a union of primitive intersections or inverses. A key difference between D$^2$CSG and all prior neural CSG models is its dedicated residual branch to assemble the potentially complex shape complement, which is subtracted from an overall shape modeled by the cover branch. With the shape complements, our network is provably general, while the weight dropout further improves compactness of the CSG tree by removing redundant primitives. We demonstrate both quantitatively and qualitatively that D$^2$CSG produces compact CSG reconstructions with superior quality and more natural primitives than all existing alternatives, especially over complex and high-genus CAD shapes.

POSTER-294: Non-Stationary Bandits with Auto-Regressive Temporal Dependency

Keywords: non-stationary bandits; autoregressive model; low-regret policy; online learning algorithms

Scores: [ 6 5 3 7 ]

Traditional multi-armed bandit (MAB) frameworks, predominantly examined under stochastic or adversarial settings, often overlook the temporal dynamics inherent in many real-world applications such as recommendation systems and online advertising. This paper introduces a novel non-stationary MAB framework that captures the temporal structure of these real-world dynamics through an auto-regressive (AR) reward structure. We propose an algorithm that integrates two key mechanisms: (i) an alternation mechanism adept at leveraging temporal dependencies to dynamically balance exploration and exploitation, and (ii) a restarting mechanism designed to discard out-of-date information. Our algorithm achieves a regret upper bound that nearly matches the lower bound, with regret measured against a robust dynamic benchmark. Finally, via a real-world case study on tourism demand prediction, we demonstrate both the efficacy of our algorithm and the broader applicability of our techniques to more complex, rapidly evolving time series.

POSTER-295: Optimistic Active Exploration of Dynamical Systems

Keywords: Active Exploration Reinforcement Learning Dynamical Systems

Scores: [ 5 5 5 6 6 6 ]

Reinforcement learning algorithms commonly seek to optimize policies for solving one particular task. How should we explore an unknown dynamical system such that the estimated model allows us to solve multiple downstream tasks in a zero-shot manner? In this paper, we address this challenge, by developing an algorithm -- OPAX -- for active exploration. OPAX uses well-calibrated probabilistic models to quantify the epistemic uncertainty about the unknown dynamics. It optimistically---w.r.t. to plausible dynamics---maximizes the information gain between the unknown dynamics and state observations. We show how the resulting optimization problem can be reduced to an optimal control problem that can be solved at each episode using standard approaches. We analyze our algorithm for general models, and, in the case of Gaussian process dynamics, we give a sample complexity bound andshow that the epistemic uncertainty converges to zero. In our experiments, we compare OPAX with other heuristic active exploration approaches on several environments. Our experiments show that OPAX is not only theoretically sound but also performs well for zero-shot planning on novel downstream tasks.

POSTER-296: Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts

Keywords: Neuro-Symbolic Integration Trustworthy AI Concept Learning Learning Shortcuts Mitigation Strategies

Scores: [ 7 7 6 7 ]

Neuro-Symbolic (NeSy) predictive models hold the promise of improved compliance with given constraints, systematic generalization, and interpretability, as they allow to infer labels that are consistent with some prior knowledge by reasoning over high-level concepts extracted from sub-symbolic inputs. It was recently shown that NeSy predictors are affected by reasoning shortcuts: they can attain high accuracy but by leveraging concepts with \textit{unintended semantics}, thus coming short of their promised advantages. Yet, a systematic characterization of reasoning shortcuts and of potential mitigation strategies is missing. This work fills this gap by characterizing them as unintended optima of the learning objective and identifying four key conditions behind their occurrence. Based on this, we derive several natural mitigation strategies, and analyze their efficacy both theoretically and empirically. Our analysis shows reasoning shortcuts are difficult to deal with, casting doubts on the trustworthiness and interpretability of existing NeSy solutions.

POSTER-297: Emergent Communication in Interactive Sketch Question Answering

Keywords: Emergent communication Interactive Question Answering

Scores: [ 7 6 4 4 ]

Vision-based emergent communication (EC) aims to learn to communicate through sketches and demystify the evolution of human communication. Ironically, previous works neglect multi-round interaction, which is indispensable in human communication. To fill this gap, we first introduce a novel Interactive Sketch Question Answering (ISQA) task, where two collaborative players are interacting through sketches to answer a question about an image. To accomplish this task, we design a new and efficient interactive EC system, which can achieve an effective balance among three evaluation factors, including the question answering accuracy, drawing complexity and human interpretability. Our experimental results demonstrate that multi-round interactive mechanism facilitates tar- geted and efficient communication between intelligent agents. The code will be released.

POSTER-298: Parallel-mentoring for Offline Model-based Optimization

Keywords: offline model-based optimization bi-level optimization

Scores: [ 7 5 7 5 ]

We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores. These designs encompass a variety of domains, including materials, robots, DNA sequences, and proteins. A common approach trains a proxy on the static dataset and performs gradient ascent to obtain new designs. However, this often results in poor designs due to the proxy inaccuracies for out-of-distribution designs. Recent studies indicate that (a) gradient ascent with a mean ensemble of proxies generally outperforms simple gradient ascent, and (b) a trained proxy provides weak ranking supervision signals for design selection. Motivated by (a) and (b), we propose \(\textit{parallel-mentoring}\) as an effective and novel method that facilitates mentoring among proxies, creating a more robust ensemble to mitigate the out-of-distribution issue. We focus on the three-proxy case in the main paper and our method consists of two modules. The first module, \(\textit{voting-based pairwise supervision}\), operates on three parallel proxies and captures their ranking supervision signals as pairwise comparison labels. These labels are combined through majority voting to generate consensus labels, which incorporates ranking supervision signals from all proxies and enables mutual mentoring. Yet, label noise arises due to possible incorrect consensus. To alleviate this, we introduce an \(\textit{adaptive soft-labeling}\) module with soft-labels initialized as consensus labels. Based on bi-level optimization, this module fine-tunes proxies in the inner level and learns more accurate labels in the outer level to adaptively mentor proxies, resulting in a more robust ensemble. Experiments validate the effectiveness of our method. Our code is available here.

POSTER-299: Offline RL with Discrete Proxy Representations for Generalizability in POMDPs

Keywords: Offline RL POMDP

Scores: [ 6 4 6 7 ]

Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, real-world scenarios usually involve partial observability, which brings crucial challenges of the deployment of offline RL methods: i) the policy trained on data with full observability is not robust against the masked observations during execution, and ii) the information of which parts of observations are masked is usually unknown during training. In order to address these challenges, we present Offline RL with DiscrEte pRoxy representations (ORDER), a probabilistic framework which leverages novel state representations to improve the robustness against diverse masked observabilities. Specifically, we propose a discrete representation of the states and use a proxy representation to recover the states from masked partial observable trajectories. The training of ORDER can be compactly described as the following three steps. i) Learning the discrete state representations on data with full observations, ii) Training the decision module based on the discrete representations, and iii) Training the proxy discrete representations on the data with various partial observations, aligning with the discrete representations. We conduct extensive experiments to evaluate ORDER, showcasing its effectiveness in offline RL for diverse partially observable scenarios and highlighting the significance of discrete proxy representations in generalization performance.ORDER is a flexible framework to employ any offline RL algorithms and we hope that ORDER can pave the way for the deployment of RL policy against various partial observabilities in the real world.

POSTER-300: Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data

Keywords: model evaluation tabular synthetic data

Scores: [ 5 6 6 7 6 ]

Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications. However, accurately assessing model performance becomes challenging due to two main issues: (1) a scarcity of test data, especially for small subgroups, and (2) possible distributional shifts in the model's deployment setting, which may not align with the available test data. In this work, we introduce 3S Testing, a deep generative modeling framework to facilitate model evaluation by generating synthetic test sets for small subgroups and simulating distributional shifts. Our experiments demonstrate that 3S-Testing outperforms traditional baselines---including real test data alone---in estimating model performance on minority subgroups and under plausible distributional shifts. In addition, 3S offers intervals around its performance estimates, exhibiting superior coverage of the ground truth compared to existing approaches. Overall, these results raise the question of whether we need a paradigm shift away from limited real test data towards synthetic test data.

SPOTLIGHT-42: Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction

Keywords: Protein representation learning diffusion models self-supervised learning

Scores: [ 6 7 7 7 ]

Self-supervised pre-training methods on proteins have recently gained attention, with most approaches focusing on either protein sequences or structures, neglecting the exploration of their joint distribution, which is crucial for a comprehensive understanding of protein functions by integrating co-evolutionary information and structural characteristics. In this work, inspired by the success of denoising diffusion models in generative tasks, we propose the DiffPreT approach to pre-train a protein encoder by sequence-structure joint diffusion modeling. DiffPreT guides the encoder to recover the native protein sequences and structures from the perturbed ones along the joint diffusion trajectory, which acquires the joint distribution of sequences and structures. Considering the essential protein conformational variations, we enhance DiffPreT by a method called Siamese Diffusion Trajectory Prediction (SiamDiff) to capture the correlation between different conformers of a protein. SiamDiff attains this goal by maximizing the mutual information between representations of diffusion trajectories of structurally-correlated conformers. We study the effectiveness of DiffPreT and SiamDiff on both atom- and residue-level structure-based protein understanding tasks. Experimental results show that the performance of DiffPreT is consistently competitive on all tasks, and SiamDiff achieves new state-of-the-art performance, considering the mean ranks on all tasks. Code will be released upon acceptance.

POSTER-301: Latent Graph Inference with Limited Supervision

Keywords: Latent Graph Inference CUR Matrix Decomposition Graph Neural Networks

Scores: [ 7 7 6 7 5 ]

Latent graph inference (LGI) aims to jointly learn the underlying graph structure and node representations from data features. However, existing LGI methods commonly suffer from the issue of supervision starvation, where massive edge weights are learned without semantic supervision and do not contribute to the training loss. Consequently, these supervision-starved weights, which determine the predictions of testing samples, cannot be semantically optimal, resulting in poor generalization. In this paper, we observe that this issue is actually caused by the graph sparsification operation, which severely destroys the important connections established between pivotal nodes and labeled ones. To address this, we propose to restore the corrupted affinities and replenish the missed supervision for better LGI. The key challenge then lies in identifying the critical nodes and recovering the corrupted affinities. We begin by defining the pivotal nodes as k-hop starved nodes, which can be identified based on a given adjacency matrix. Considering the high computational burden, we further present a more efficient alternative inspired by CUR matrix decomposition. Subsequently, we eliminate the starved nodes by reconstructing the destroyed connections. Extensive experiments on representative benchmarks demonstrate that reducing the starved nodes consistently improves the performance of state-of-the-art LGI methods, especially under extremely limited supervision (6.12% improvement on Pubmed with a labeling rate of only 0.3%).

POSTER-302: Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods

Keywords: Regression calibration model recalibration conditional quantile nonparametric method

Scores: [ 4 6 6 8 ]

In this paper, we consider the uncertainty quantification problem for regression models. Specifically, we consider an individual calibration objective for characterizing the quantiles of the prediction model. While such an objective is well-motivated from downstream tasks such as newsvendor cost, the existing methods have been largely heuristic and lack of statistical guarantee in terms of individual calibration. We show via simple examples that the existing methods focusing on population-level calibration guarantees such as average calibration or sharpness can lead to harmful and unexpected results. We propose simple nonparametric calibration methods that are agnostic of the underlying prediction model and enjoy both computational efficiency and statistical consistency. Our approach enables a better understanding of the possibility of individual calibration, and we establish matching upper and lower bounds for the calibration error of our proposed methods. Technically, our analysis combines the nonparametric analysis with a covering number argument for parametric analysis, which advances the existing theoretical analyses in the literature of nonparametric density estimation and quantile bandit problems. Importantly, the nonparametric perspective sheds new theoretical insights into regression calibration in terms of the curse of dimensionality and reconciles the existing results on the impossibility of individual calibration. To our knowledge, we make the first effort to reach both individual calibration and finite-sample guarantee with minimal assumptions in terms of conformal prediction. Numerical experiments show the advantage of such a simple approach under various metrics, and also under covariates shift. We hope our work provides a simple benchmark and a starting point of theoretical ground for future research on regression calibration.

POSTER-303: Maximum State Entropy Exploration using Predecessor and Successor Representations

Keywords: Reinforcement Learning Maximum state entropy exploration Non-Markovian exploration Successor Representation

Scores: [ 6 8 5 6 ]

Animals have a developed ability to explore that aids them in important tasks such as locating food, exploring for shelter, and finding misplaced items. These exploration skills necessarily track where they have been so that they can plan for finding items with relative efficiency. Contemporary exploration algorithms often learn a less efficient exploration strategy because they either condition only on the current state or simply rely on making random open-loop exploratory moves. In this work, we propose \(\eta\psi\)-Learning, a method to learn efficient exploratory policies by conditioning on past episodic experience to make the next exploratory move. Specifically, \(\eta\psi\)-Learning learns an exploration policy that maximizes the entropy of the state visitation distribution of a single trajectory. Furthermore, we demonstrate how variants of the predecessor representation and successor representations can be combined to predict the state visitation entropy. Our experiments demonstrate the efficacy of \(\eta\psi\)-Learning to strategically explore the environment and maximize the state coverage with limited samples.

POSTER-304: Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

Keywords: Optimization Machine Learning Extragradient Methods Min-Max Optimization

Scores: [ 7 6 3 6 ]

Single-call stochastic extragradient methods, like stochastic past extragradient (SPEG) and stochastic optimistic gradient (SOG), have gained a lot of interest in recent years and are one of the most efficient algorithms for solving large-scale min-max optimization and variational inequalities problems (VIP) appearing in various machine learning tasks. However, despite their undoubted popularity, current convergence analyses of SPEG and SOG require strong assumptions like bounded variance or growth conditions. In addition, several important questions regarding the convergence properties of these methods are still open, including mini-batching, efficient step-size selection, and convergence guarantees under different sampling strategies. In this work, we address these questions and provide convergence guarantees for two large classes of structured non-monotone VIPs: (i) quasi-strongly monotone problems (a generalization of strongly monotone problems) and (ii) weak Minty variational inequalities (a generalization of monotone and Minty VIPs). We introduce the expected residual condition, explain its benefits, and show how it allows us to obtain a strictly weaker bound than previously used growth conditions, expected co-coercivity, or bounded variance assumptions. Finally, our convergence analysis holds under the arbitrary sampling paradigm, which includes importance sampling and various mini-batching strategies as special cases.

POSTER-305: Federated Compositional Deep AUC Maximization

Keywords: federated learning compositional optimization minimax optimization AUC maximization

Scores: [ 3 7 5 ]

Federated learning has attracted increasing attention due to the promise of balancing privacy and large-scale learning; numerous approaches have been proposed. However, most existing approaches focus on problems with balanced data, and prediction performance is far from satisfactory for many real-world applications where the number of samples in different classes is highly imbalanced. To address this challenging problem, we developed a novel federated learning method for imbalanced data by directly optimizing the area under curve (AUC) score. In particular, we formulate the AUC maximization problem as a federated compositional minimax optimization problem, develop a local stochastic compositional gradient descent ascent with momentum algorithm, and provide bounds on the computational and communication complexities of our algorithm. To the best of our knowledge, this is the first work to achieve such favorable theoretical results. Finally, extensive experimental results confirm the efficacy of our method.

POSTER-306: PPi: Pretraining Brain Signal Model for Patient-independent Seizure Detection

Keywords: Brain signal Seizure detection Pretraining Domain generalization

Scores: [ 5 6 8 7 5 6 ]

Automated seizure detection is of great importance to epilepsy diagnosis and treatment. An emerging method used in seizure detection, stereoelectroencephalography (SEEG), can provide detailed and stereoscopic brainwave information. However, modeling SEEG in clinical scenarios will face challenges like huge domain shi