ICML 2022 Papers

mini compact topic detail

Communicating via Markov Decision Processes

Inferring Cause and Effect in the Presence of Heteroscedastic Noise

Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games

Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis

Anticorrelated Noise Injection for Improved Generalization

Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation

When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee

Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning

The Primacy Bias in Deep Reinforcement Learning

Understanding Gradient Descent on the Edge of Stability in Deep Learning

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation

On Distribution Shift in Learning-based Bug Detectors

SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Spatial-Channel Token Distillation for Vision MLPs

Understanding The Robustness in Vision Transformers

NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields

Measuring Representational Robustness of Neural Networks Through Shared Invariances

Efficient Approximate Inference for Stationary Kernel on Frequency Domain

Goal Misgeneralization in Deep Reinforcement Learning

Topology-aware Generalization of Decentralized SGD

Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation

Decision-Focused Learning: Through the Lens of Learning to Rank

On Implicit Bias in Overparameterized Bilevel Optimization

Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond

Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs

Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing

Channel Importance Matters in Few-Shot Image Classification

RECAPP: Crafting a More Efficient Catalyst for Convex Optimization

From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model

Supervised Off-Policy Ranking

Steerable 3D Spherical Neurons

Neural Inverse Kinematic

SE(3) Equivariant Graph Neural Networks with Complete Local Frames

DNNR: Differential Nearest Neighbors Regression

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

Active Sampling for Min-Max Fairness

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences

More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize

The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks

Towards Understanding Sharpness-Aware Minimization

AGNAS: Attention-Guided Micro- and Macro-Architecture Search

Improving Policy Optimization with Generalist-Specialist Learning

Short-Term Plasticity Neurons Learning to Learn and Forget

Adaptive Model Design for Markov Decision Process

Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors

Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering

Matching Learned Causal Effects of Neural Networks with Domain Priors

Bayesian Deep Embedding Topic Meta-Learner

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation

Accurate Quantization of Measures via Interacting Particle-based Optimization

Planning with Diffusion for Flexible Behavior Synthesis

An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear Programming

Equivariant Priors for compressed sensing with unknown orientation

Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps

On the Role of Discount Factor in Offline Reinforcement Learning

Adapting the Linearised Laplace Model Evidence for Modern Deep Learning

Communication-Efficient Adaptive Federated Learning

Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold

Continual Learning via Sequential Function-Space Variational Inference

Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization

Do More Negative Samples Necessarily Hurt In Contrastive Learning?

Fast Population-Based Reinforcement Learning on a Single Machine

NeuralEF: Deconstructing Kernels by Deep Neural Networks

Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making

Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data

Robust Training of Neural Networks Using Scale Invariant Architectures

Generalization and Robustness Implications in Object-Centric Learning

Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

Multicoated Supermasks Enhance Hidden Networks

Time Is MattEr: Temporal Self-supervision for Video Transformers

Privacy for Free: How does Dataset Condensation Help Privacy?

Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning

Stable Conformal Prediction Sets

Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations

Selective Regression under Fairness Criteria

Towards Scaling Difference Target Propagation by Learning Backprop Targets

Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?

Personalized Federated Learning through Local Memorization

SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding

Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm

On the Adversarial Robustness of Causal Algorithmic Recourse

Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning

Coin Flipping Neural Networks

Neurotoxin: Durable Backdoors in Federated Learning

Dataset Condensation with Contrastive Signals

How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation

Deep Network Approximation in Terms of Intrinsic Parameters

A Convergent and Dimension-Independent Min-Max Optimization Algorithm

Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization

Implicit Regularization with Polynomial Growth in Deep Tensor Factorization

Demystifying the Adversarial Robustness of Random Transformation Defenses

Marginal Tail-Adaptive Normalizing Flows

Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging

NP-Match: When Neural Processes meet Semi-Supervised Learning

Representation Topology Divergence: A Method for Comparing Neural Network Representations.

Understanding Contrastive Learning Requires Incorporating Inductive Biases

Neural Implicit Dictionary Learning via Mixture-of-Expert Training

POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Retroformer: Pushing the Limits of End-to-end Retrosynthesis Transformer

SpaceMAP: Visualizing High-Dimensional Data by Space Expansion

Meta-Learning Hypothesis Spaces for Sequential Decision-making

Lazy Estimation of Variable Importance for Large Neural Networks

A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization

Partial disentanglement for domain adaptation

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path

Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness

Langevin Monte Carlo for Contextual Bandits

Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems

Tractable Uncertainty for Structure Learning

Multi-slots Online Matching with High Entropy

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

Self-Supervised Models of Audio Effectively Explain Human Cortical Responses to Speech

GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks

Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning

Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling

On the Generalization Analysis of Adversarial Learning

Extended Unconstrained Features Model for Exploring Deep Neural Collapse

Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization

Zero-Shot Reward Specification via Grounded Natural Language

VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix

Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint

Generative Cooperative Networks for Natural Language Generation

Multi-scale Feature Learning Dynamics: Insights for Double Descent

On Convergence of Gradient Descent Ascent: A Tight Local Analysis

Reachability Constrained Reinforcement Learning

A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design

Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection

Differentially Private Coordinate Descent for Composite Empirical Risk Minimization

Calibrated Learning to Defer with One-vs-All Classifiers

Multiclass learning with margin: exponential rates with no bias-variance trade-off

Prompting Decision Transformer for Few-Shot Policy Generalization

TSPipe: Learn from Teacher Faster with Pipelines

Self-conditioning Pre-Trained Language Models

Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models

Subspace Learning for Effective Meta-Learning

The power of first-order smooth optimization for black-box non-smooth problems

Proving Theorems using Incremental Learning and Hindsight Experience Replay

Rethinking Attention-Model Explainability through Faithfulness Violation Test

Inductive Biases and Variable Creation in Self-Attention Mechanisms

A data-driven approach for learning to control computers

Causal Imitation Learning under Temporally Correlated Noise

Delayed Reinforcement Learning by Imitation

Minimizing Control for Credit Assignment with Strong Feedback

Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems

ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks

CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer

On the Robustness of CountSketch to Adaptive Inputs

An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn

Utilizing Expert Features for Contrastive Learning of Time-Series Representations

Region-Based Semantic Factorization in GANs

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses

The Teaching Dimension of Regularized Kernel Learners

Selling Data To a Machine Learner: Pricing via Costly Signaling

Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization

Hindering Adversarial Attacks with Implicit Neural Representations

Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning

Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology

Context-Aware Drift Detection

Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time

Efficient Learning for AlphaZero via Path Consistency

Zero-shot AutoML with Pretrained Models

Offline RL Policies Should Be Trained to be Adaptive

Improving Out-of-Distribution Robustness via Selective Augmentation

Feature Learning and Signal Propagation in Deep Neural Networks

Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters

LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation

Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

Bayesian Model Selection, the Marginal Likelihood, and Generalization

Structure-Aware Transformer for Graph Representation Learning

Generalized Leverage Scores: Geometric Interpretation and Applications

Flow-Guided Sparse Transformer for Video Deblurring

FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models

Learning from a Learning User for Optimal Recommendations

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Modular Conformal Calibration

PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs

Private optimization in the interpolation regime: faster rates and hardness results

Neuron Dependency Graphs: A Causal Abstraction of Neural Networks

Searching for BurgerFormer with Micro-Meso-Macro Space Design

Rethinking Graph Neural Networks for Anomaly Detection

The Geometry of Robust Value Functions

A Tighter Analysis of Spectral Clustering, and Beyond

Directed Acyclic Transformer for Non-Autoregressive Machine Translation

Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

Exact Learning of Preference Structure: Single-peaked Preferences and Beyond

Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four

Boosting Graph Structure Learning with Dummy Nodes

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents

Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent

Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees

Sequential- and Parallel- Constrained Max-value Entropy Search via Information Lower Bound

Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets

A Statistical Manifold Framework for Point Cloud Data

Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification

Iterative Double Sketching for Faster Least-Squares Optimization

Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing

The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

Optimizing Tensor Network Contraction Using Reinforcement Learning

Distribution Regression with Sliced Wasserstein Kernels

Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding

Understanding Doubly Stochastic Clustering

Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions

On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback

Set Based Stochastic Subsampling

Neural Tangent Kernel Analysis of Deep Narrow Neural Networks

Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis

Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology

Co-training Improves Prompt-based Learning for Large Language Models

Variational Feature Pyramid Networks

Probabilistic Bilevel Coreset Selection

Efficient Distributionally Robust Bayesian Optimization with Worst-case Sensitivity

Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning

XAI for Transformers: Better Explanations through Conservative Propagation

General-purpose, long-context autoregressive modeling with Perceiver AR

Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent

TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm

Flashlight: Enabling Innovation in Tools for Machine Learning

Model Agnostic Sample Reweighting for Out-of-Distribution Learning

Nonparametric Involutive Markov Chain Monte Carlo

Identity-Disentangled Adversarial Augmentation for Self-supervised Learning

Fast and Provable Nonconvex Tensor RPCA

Certified Robustness Against Natural Language Attacks by Causal Intervention

A Simple Unified Framework for High Dimensional Bandit Problems

Interventional Contrastive Learning with Meta Semantic Regularizer

Parametric Visual Program Induction with Function Modularization

Generalized Beliefs for Cooperative AI

Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets

Unaligned Supervision for Automatic Music Transcription in The Wild

Fisher SAM: Information Geometry and Sharpness Aware Minimisation

The Algebraic Path Problem for Graph Metrics

Overcoming Oscillations in Quantization-Aware Training

Individual Reward Assisted Multi-Agent Reinforcement Learning

Causal Inference Through the Structural Causal Marginal Problem

Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation

Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation

SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation

Permutation Search of Tensor Network Structures via Local Sampling

Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups

AnyMorph: Learning Transferable Polices By Inferring Agent Morphology

Adaptive Conformal Predictions for Time Series

Unified Scaling Laws for Routed Language Models

Bayesian Optimization for Distributionally Robust Chance-constrained Problem

Provable Domain Generalization via Invariant-Feature Subspace Recovery

Revisiting Consistency Regularization for Deep Partial Label Learning

PoF: Post-Training of Feature Extractor for Improving Generalization

A Closer Look at Smoothness in Domain Adversarial Training

SpeqNets: Sparsity-aware permutation-equivariant graph networks

Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory

Fast Lossless Neural Compression with Integer-Only Discrete Flows

How Powerful are Spectral Graph Neural Networks

A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Proximal Exploration for Model-guided Protein Sequence Design

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations

Data Augmentation as Feature Manipulation

Efficient Low Rank Convex Bounds for Pairwise Discrete Graphical Models

UniRank: Unimodal Bandit Algorithms for Online Ranking

VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training

Label-Descriptive Patterns and Their Application to Characterizing Classification Errors

Online and Consistent Correlation Clustering

FedNest: Federated Bilevel, Minimax, and Compositional Optimization

Near-optimal rate of consistency for linear models with missing values

Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits

Bayesian Optimization under Stochastic Delayed Feedback

Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback

Learning of Cluster-based Feature Importance for Electronic Health Record Time-series

Global Optimization of K-Center Clustering

EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning

Variational nearest neighbor Gaussian process

A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix Estimation

Generalized Data Distribution Iteration

Anytime Information Cascade Popularity Prediction via Self-Exciting Processes

Secure Quantized Training for Deep Learning

Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime

Improving Adversarial Robustness via Mutual Information Estimation

Black-Box Tuning for Language-Model-as-a-Service

A Context-Integrated Transformer-Based Neural Network for Auction Design

Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert

Neurocoder: General-Purpose Computation Using Stored Neural Programs

Learning Infinite-horizon Average-reward Markov Decision Process with Constraints

Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models

Sparse Invariant Risk Minimization

Winning the Lottery Ahead of Time: Efficient Early Network Pruning

Implicit Bias of the Step Size in Linear Diagonal Neural Networks

Intriguing Properties of Input-Dependent Randomized Smoothing

Latent Diffusion Energy-Based Model for Interpretable Text Modelling

Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes

Bregman Neural Networks

ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias

Graph Neural Architecture Search Under Distribution Shifts

Quantifying and Learning Linear Symmetry-Based Disentanglement

Certifying Out-of-Domain Generalization for Blackbox Functions

Constants Matter: The Performance Gains of Active Learning

AutoSNN: Towards Energy-Efficient Spiking Neural Networks

A Modern Self-Referential Weight Matrix That Learns to Modify Itself

The Complexity of k-Means Clustering when Little is Known

Gradient Based Clustering

Modeling Adversarial Noise for Adversarial Training

Balancing Discriminability and Transferability for Source-Free Domain Adaptation

Closed-Form Diffeomorphic Transformations for Time Series Alignment

Dynamic Regret of Online Markov Decision Processes

A Multi-objective / Multi-task Learning Framework Induced by Pareto Stationarity

Spectral Representation of Robustness Measures for Optimization Under Input Uncertainty

Individual Preference Stability for Clustering

Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics

Importance Weighted Kernel Bayes' Rule

Instrumental Variable Regression with Confounder Balancing

Optimal Clustering with Noisy Queries via Multi-Armed Bandit

Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training

It’s Raw! Audio Generation with State-Space Models

Nyström Kernel Mean Embeddings

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets

An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings

Causal Transformer for Estimating Counterfactual Outcomes

A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization

Convolutional and Residual Networks Provably Contain Lottery Tickets

Interpretable Off-Policy Learning via Hyperbox Search

Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation

UNIREX: A Unified Learning Framework for Language Model Rationale Extraction

Self-Organized Polynomial-Time Coordination Graphs

Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning

Predicting Out-of-Distribution Error with the Projection Norm

Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation

Generative Modeling for Multi-task Visual Learning

An Intriguing Property of Geophysics Inversion

Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning

A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving

Let Invariant Rationale Discovery Inspire Graph Contrastive Learning

Fast rates for noisy interpolation require rethinking the effect of inductive bias

Provably Adversarially Robust Nearest Prototype Classifiers

Continual Learning with Guarantees via Weight Interval Constraints

You Only Cut Once: Boosting Data Augmentation with a Single Cut

A Dynamical System Perspective for Lipschitz Neural Networks

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)

Strategic Representation

A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1

On the Learning of Non-Autoregressive Transformers

Actor-Critic based Improper Reinforcement Learning

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums

Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency

Understanding and Improving Knowledge Graph Embedding for Entity Alignment

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification

A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing

Dialog Inpainting: Turning Documents into Dialogs

How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity

Measuring dissimilarity with diffeomorphism invariance

Learning Pseudometric-based Action Representations for Offline Reinforcement Learning

Fast Composite Optimization and Statistical Recovery in Federated Learning

Efficiently Learning the Topology and Behavior of a Networked Dynamical System Via Active Queries

MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer

Fair and Fast k-Center Clustering for Data Summarization

Deep Reference Priors: What is the best way to pretrain a model?

Improving Task-free Continual Learning by Distributionally Robust Memory Evolution

ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning

Continual Repeated Annealed Flow Transport Monte Carlo

HyperImpute: Generalized Iterative Imputation with Automatic Model Selection

Revisiting Online Submodular Minimization: Gap-Dependent Regret Bounds, Best of Both Worlds and Adversarial Robustness

Data Scaling Laws in NMT: The Effect of Noise and Architecture

Improving Mini-batch Optimal Transport via Partial Transportation

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

Learning Iterative Reasoning through Energy Minimization

Efficient Computation of Higher-Order Subgraph Attribution via Message Passing

Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Robust Imitation Learning against Variations in Environment Dynamics

Accelerated Federated Learning with Decoupled Adaptive Optimization

A Consistent and Efficient Evaluation Strategy for Attribution Methods

Private Adaptive Optimization with Side information

A Difference Standardization Method for Mutual Transfer Learning

Memory-Based Model Editing at Scale

Revisiting End-to-End Speech-to-Text Translation From Scratch

Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning

Causal structure-based root cause analysis of outliers

Learning to Estimate and Refine Fluid Motion with Physical Dynamics

Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning

Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters

Generalised Policy Improvement with Geometric Policy Composition

Popular decision tree algorithms are provably noise tolerant

Only tails matter: Average-Case Universality and Robustness in the Convex Regime

Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning

Scalable Deep Reinforcement Learning Algorithms for Mean Field Games

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

DAVINZ: Data Valuation using Deep Neural Networks at Initialization

What Dense Graph Do You Need for Self-Attention?

Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications

Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization

Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm

A Unified View on PAC-Bayes Bounds for Meta-Learning

Online Continual Learning through Mutual Information Maximization

Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization

Learning Dynamics and Generalization in Deep Reinforcement Learning

Certified Adversarial Robustness Under the Bounded Support Set

ASAP.SGD: Instance-based Adaptiveness to Staleness in Asynchronous SGD

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities

Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks

Near-Optimal Learning of Extensive-Form Games with Imperfect Information

Contrastive Learning with Boosted Memorization

Improving Language Models by Retrieving from Trillions of Tokens

UAST: Uncertainty-Aware Siamese Tracking

Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness

Online Learning for Min Sum Set Cover and Pandora’s Box

Faster Privacy Accounting via Evolving Discretization

Gradient-Free Method for Heavily Constrained Nonconvex Optimization

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning

A Temporal-Difference Approach to Policy Gradient Estimation

Framework for Evaluating Faithfulness of Local Explanations

Learning Multiscale Transformer Models for Sequence Generation

Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs

Mirror Learning: A Unifying Framework of Policy Optimisation

Denoised MDPs: Learning World Models Better Than the World Itself

Identifiability Conditions for Domain Adaptation

Nested Bandits

Federated Minimax Optimization: Improved Convergence Analyses and Algorithms

A Simple yet Universal Strategy for Online Convex Optimization

SPDY: Accurate Pruning with Speedup Guarantees

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

Functional Output Regression with Infimal Convolution: Exploring the Huber and $\epsilon$-insensitive Losses

Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems

Smoothed Adversarial Linear Contextual Bandits with Knapsacks

A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines

On Collective Robustness of Bagging Against Data Poisoning

CITRIS: Causal Identifiability from Temporal Intervened Sequences

Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model

Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers

Reinforcement Learning with Action-Free Pre-Training from Videos

A new similarity measure for covariate shift with applications to nonparametric regression

State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks

Self-supervised learning with random-projection quantizer for speech recognition

Learning Symmetric Embeddings for Equivariant World Models

How Tempering Fixes Data Augmentation in Bayesian Neural Networks

Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes

Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming

HousE: Knowledge Graph Embedding with Householder Parameterization

Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation

Investigating Why Contrastive Learning Benefits Robustness against Label Noise

Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity

Frustratingly Easy Transferability Estimation

Minimum Cost Intervention Design for Causal Effect Identification

Action-Sufficient State Representation Learning for Control with Structural Constraints

Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems

GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing

Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning

Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Tackling covariate shift with node-based Bayesian neural networks

DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning

Transfer and Marginalize: Explaining Away Label Noise with Privileged Information

Staged Training for Transformer Language Models

Deletion Robust Submodular Maximization over Matroids

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic Games

Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm

Estimating and Penalizing Induced Preference Shifts in Recommender Systems

The Unsurprising Effectiveness of Pre-Trained Vision Models for Control

Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts

Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation

Efficient Learning of CNNs using Patch Based Features

Biological Sequence Design with GFlowNets

One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes

Private frequency estimation via projective geometry

Counterfactual Prediction for Outcome-Oriented Treatments

3D Infomax improves GNNs for Molecular Property Prediction

Generating Distributional Adversarial Examples to Evade Statistical Detectors

How to Leverage Unlabeled Data in Offline Reinforcement Learning

Linear Adversarial Concept Erasure

Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer

MetAug: Contrastive Learning via Meta Feature Augmentation

Lie Point Symmetry Data Augmentation for Neural PDE Solvers

Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models

Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function

Conformal Prediction Sets with Limited False Positives

Personalized Federated Learning via Variational Bayesian Inference

Path-Gradient Estimators for Continuous Normalizing Flows

Consistent Polyhedral Surrogates for Top-k Classification and Variants

Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation

Interactive Inverse Reinforcement Learning for Cooperative Games

Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms

Be Like Water: Adaptive Floating Point for Machine Learning

Diffusion bridges vector quantized variational autoencoders

Deduplicating Training Data Mitigates Privacy Risks in Language Models

Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent

Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

Scalable Deep Gaussian Markov Random Fields for General Graphs

Transformer Quality in Linear Time

Visual Attention Emerges from Recurrent Sparse Reconstruction

Confidence Score for Source-Free Unsupervised Domain Adaptation

Unsupervised Image Representation Learning with Deep Latent Particles

Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization

A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions

IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data

On the Surrogate Gap between Contrastive and Supervised Losses

Understanding Instance-Level Impact of Fairness Constraints

Robust Group Synchronization via Quadratic Programming

Deep Causal Metric Learning

Flowformer: Linearizing Transformers with Conservation Flows

Graph-Coupled Oscillator Networks

Variational Inference for Infinitely Deep Neural Networks

Reverse Engineering the Neural Tangent Kernel

Low-Precision Stochastic Gradient Langevin Dynamics

Matching Normalizing Flows and Probability Paths on Manifolds

Asymptotically-Optimal Gaussian Bandits with Side Observations

Sparse Double Descent: Where Network Pruning Aggravates Overfitting

Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness

Distributionally-Aware Kernelized Bandit Problems for Risk Aversion

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games

Principled Knowledge Extrapolation with GANs

Not All Poisons are Created Equal: Robust Training against Data Poisoning

DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training

DynaMixer: A Vision MLP Architecture with Dynamic Mixing

Fenrir: Physics-Enhanced Regression for Initial Value Problems

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces

LCANets: Lateral Competition Improves Robustness Against Corruption and Attack

PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation

Prototype-Anchored Learning for Learning with Imperfect Annotations

Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images

Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers

Adaptive Gaussian Process Change Point Detection

Hardness and Algorithms for Robust and Sparse Optimization

Multi Resolution Analysis (MRA) for Approximate Self-Attention

A Functional Information Perspective on Model Interpretation

PAC-Net: A Model Pruning Approach to Inductive Transfer Learning

Robust Policy Learning over Multiple Uncertainty Sets

Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization

Fast Finite Width Neural Tangent Kernel

Robustness in Multi-Objective Submodular Optimization: a Quantile Approach

Optimal Estimation of Policy Gradient via Double Fitted Iteration

Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation

Rethinking Fano’s Inequality in Ensemble Learning

Convergence of Uncertainty Sampling for Active Learning

The Role of Deconfounding in Meta-learning

Active fairness auditing

FITNESS: (Fine Tune on New and Similar Samples) to detect anomalies in streams with drift and outliers

Deep Hierarchy in Bandits

Adversarially Trained Actor Critic for Offline Reinforcement Learning

Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding

Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series

GACT: Activation Compressed Training for Generic Network Architectures

Disentangling Disease-related Representation from Obscure for Disease Prediction

Provable Reinforcement Learning with a Short-Term Memory

Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense

Secure Distributed Training at Scale

Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance

Neuro-Symbolic Hierarchical Rule Induction

pathGCN: Learning General Graph Spatial Operators from Paths

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization

Conditional GANs with Auxiliary Discriminative Classifier

Retrieval-Augmented Reinforcement Learning

Generative Flow Networks for Discrete Probabilistic Modeling

Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks

Adversarially trained neural representations are already as robust as biological neural representations

A Parametric Class of Approximate Gradient Updates for Policy Optimization

Interactively Learning Preference Constraints in Linear Bandits

Robust Training under Label Noise by Over-parameterization

Causal Conceptions of Fairness and their Consequences

Flow-based Recurrent Belief State Learning for POMDPs

Approximate Bayesian Computation with Domain Expert in the Loop

Multi-Task Learning as a Bargaining Game

Investigating Generalization by Controlling Normalized Margin

Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations

Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits

MAML and ANIL Provably Learn Representations

Model-Free Opponent Shaping

Optimizing Sequential Experimental Design with Deep Reinforcement Learning

Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features

The Multivariate Community Hawkes Model for Dependent Relational Events in Continuous-time Networks

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression

Variational Inference with Locally Enhanced Bounds for Hierarchical Models

Branching Reinforcement Learning

On the Convergence of the Shapley Value in Parametric Bayesian Learning Games

Metric-Fair Classifier Derandomization

Partial Counterfactual Identification from Observational and Experimental Data

Correlated Quantization for Distributed Mean Estimation and Optimization

Transformers are Meta-Reinforcement Learners

Temporal Difference Learning for Model Predictive Control

PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance

Fair Generalized Linear Models with a Convex Penalty

A Simple Guard for Learned Optimizers

Federated Learning with Positive and Unlabeled Data

A Langevin-like Sampler for Discrete Distributions

Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile

Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation

Data-SUITE: Data-centric identification of in-distribution incongruous examples

LyaNet: A Lyapunov Framework for Training Neural ODEs

The Neural Race Reduction: Dynamics of Abstraction in Gated Networks

Bit Prioritization in Variational Autoencoders via Progressive Coding

Wide Neural Networks Forget Less Catastrophically

Model Selection in Batch Policy Optimization

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

To Smooth or Not? When Label Smoothing Meets Noisy Labels

Improving Screening Processes via Calibrated Subset Selection

Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum

A Regret Minimization Approach to Multi-Agent Control

Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language

Streaming Inference for Infinite Feature Models

Examining Scaling and Transfer of Language Model Architectures for Machine Translation

On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games

FedNL: Making Newton-Type Methods Applicable to Federated Learning

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification

Exact Optimal Accelerated Complexity for Fixed-Point Iterations

Fairness with Adaptive Weights

Efficient Representation Learning via Adaptive Context Pooling

Anarchic Federated Learning

A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks

On Measuring Causal Contributions via do-interventions

Making Linear MDPs Practical via Contrastive Representation Learning

Building Robust Ensembles via Margin Boosting

On Last-Iterate Convergence Beyond Zero-Sum Games

Learning fair representation with a parametric integral probability metric

Extracting Latent State Representations with Linear Dynamics from Rich Observations

Forward Operator Estimation in Generative Models with Kernel Transfer Operators

Decentralized Online Convex Optimization in Networked Systems

Burst-Dependent Plasticity and Dendritic Amplification Support Target-Based Learning and Hierarchical Imitation Learning

Contextual Bandits with Large Action Spaces: Made Practical

Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training

On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Feature Space Particle Inference for Neural Network Ensembles

Linear Complexity Randomized Self-attention Mechanism

Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP

Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems

Robust Counterfactual Explanations for Tree-Based Ensembles

A New Perspective on the Effects of Spectrum in Graph Neural Networks

The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces

Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces

Datamodels: Understanding Predictions with Data and Data with Predictions

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics

ActiveHedge: Hedge meets Active Learning

Principal Component Flows

Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation

Learning to Separate Voices by Spatial Regions

On Numerical Integration in Neural Ordinary Differential Equations

Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments

On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum

Domain Adaptation for Time Series Forecasting via Attention Sharing

DNA: Domain Generalization with Diversified Neural Averaging

Architecture Agnostic Federated Learning for Neural Networks

Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time

Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning

Understanding Robust Generalization in Learning Regular Languages

Minimax M-estimation under Adversarial Contamination

Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring

A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms

Easy Variational Inference for Categorical Models via an Independent Binary Approximation

Training Your Sparse Neural Network Better with Any Mask

How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection

Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning

Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms

On Learning Mixture of Linear Regressions in the Non-Realizable Setting

Sparsity in Partially Controllable Linear Systems

On the Equivalence Between Temporal and Static Equivariant Graph Representations

ButterflyFlow: Building Invertible Layers with Butterfly Matrices

Structured Stochastic Gradient MCMC

Scaling Out-of-Distribution Detection for Real-World Settings

Towards Uniformly Superhuman Autonomy via Subdominance Minimization

RUMs from Head-to-Head Contests

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets

Learning inverse folding from millions of predicted structures

When Are Linear Stochastic Bandits Attackable?

VarScene: A Deep Generative Model for Realistic Scene Graph Synthesis

Streaming Algorithms for High-Dimensional Robust Statistics

Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering

Distributionally Robust $Q$-Learning

Optimally Controllable Perceptual Lossy Compression

On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis

Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes

Learning Stochastic Shortest Path with Linear Function Approximation

Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification

Exploiting Independent Instruments: Identification and Distribution Generalization

Thompson Sampling for Robust Transfer in Multi-Task Bandits

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

A Model-Agnostic Randomized Learning Framework based on Random Hypothesis Subspace Sampling

Cycle Representation Learning for Inductive Relation Prediction

A Simple Reward-free Approach to Constrained Reinforcement Learning

Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition

Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models

Coordinated Double Machine Learning

Causal Dynamics Learning for Task-Independent State Abstraction

Identification of Linear Non-Gaussian Latent Hierarchical Structure

Robust Multi-Objective Bayesian Optimization Under Input Noise

FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning

EqR: Equivariant Representations for Data-Efficient Reinforcement Learning

Robustness Verification for Contrastive Learning

Does the Data Induce Capacity Control in Deep Learning?

Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator

A Framework for Learning to Request Rich and Contextually Useful Information from Humans

Regret Minimization with Performative Feedback

Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models.

Variational Wasserstein gradient flow

Hermite Polynomial Features for Private Data Generation

N-Penetrate: Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations

Locally Sparse Neural Networks for Tabular Biomedical Data

Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

On Non-local Convergence Analysis of Deep Linear Networks

No-Regret Learning in Partially-Informed Auctions

Universal and data-adaptive algorithms for model selection in linear contextual bandits

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy

Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass Filters

De novo mass spectrometry peptide sequencing with a transformer model

Learning Augmented Binary Search Trees

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification

A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games

Probabilistically Robust Learning: Balancing Average- and Worst-case Performance

Differentially Private Community Detection for Stochastic Block Models

A Study on the Ramanujan Graph Property of Winning Lottery Tickets

Local Augmentation for Graph Neural Networks

Learning from Counterfactual Links for Link Prediction

H-Consistency Bounds for Surrogate Loss Minimizers

VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

A deep convolutional neural network that is invariant to time rescaling

Improved Regret for Differentially Private Exploration in Linear MDP

Supervised Learning with General Risk Functionals

Combining Diverse Feature Priors

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling

Do Differentiable Simulators Give Better Policy Gradients?

Entropic Causal Inference: Graph Identifiability

Counterfactual Transportability: A Formal Approach

BAMDT: Bayesian Additive Semi-Multivariate Decision Trees for Nonparametric Regression

Feature selection using e-values

Augment with Care: Contrastive Learning for Combinatorial Problems

LIMO: Latent Inceptionism for Targeted Molecule Generation

Object Permanence Emerges in a Random Walk along Memory

Imitation Learning by Estimating Expertise of Demonstrators

Neural Laplace: Learning diverse classes of differential equations in the Laplace domain

Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning

Random Gegenbauer Features for Scalable Kernel Methods

Proximal and Federated Random Reshuffling

Neural Tangent Kernel Empowered Federated Learning

Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood

Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost

An Analytical Update Rule for General Policy Optimization

Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks

Meaningfully debugging model mistakes using conceptual counterfactual explanations

The State of Sparse Training in Deep Reinforcement Learning

Diffusion Models for Adversarial Purification

Multirate Training of Neural Networks

A Natural Actor-Critic Framework for Zero-Sum Markov Games

Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm

Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks

Resilient and Communication Efficient Learning for Heterogeneous Federated Systems

DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks

Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes

Efficient Online ML API Selection for Multi-Label Classification Tasks

Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra

Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics

Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning

Discrete Tree Flows via Tree-Structured Permutations

On Transportation of Mini-batches: A Hierarchical Approach

Understanding the unstable convergence of gradient descent

Modeling Strong and Human-Like Gameplay with KL-Regularized Search

Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling

Going Deeper into Permutation-Sensitive Graph Neural Networks

Online Decision Transformer

Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints

LSB: Local Self-Balancing MCMC in Discrete Spaces

Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning

Sketching Algorithms and Lower Bounds for Ridge Regression

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

Differentially Private Maximal Information Coefficients

Accelerating Shapley Explanation via Contributive Cooperator Selection

More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees

Antibody-Antigen Docking and Design via Hierarchical Structure Refinement

When and How Mixup Improves Calibration

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Hessian-Free High-Resolution Nesterov Acceleration For Sampling

DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Neural Inverse Transform Sampler

Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees

Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach

On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning

Symmetric Machine Theory of Mind

COAT: Measuring Object Compositionality in Emergent Representations

Discrete Probabilistic Inverse Optimal Transport

Stability Based Generalization Bounds for Exponential Family Langevin Dynamics

Role-based Multiplex Network Embedding

Bayesian Imitation Learning for End-to-End Mobile Manipulation

Constrained Variational Policy Optimization for Safe Reinforcement Learning

POEM: Out-of-Distribution Detection with Posterior Sampling

Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information

Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits

Federated Learning with Partial Model Personalization

Entropic Gromov-Wasserstein between Gaussian Distributions

Debiaser Beware: Pitfalls of Centering Regularized Transport Maps

A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources

G-Mixup: Graph Data Augmentation for Graph Classification

Selective Network Linearization for Efficient Private Inference

Dual Perspective of Label-Specific Feature Learning for Multi-Label Classification

Measure Estimation in the Barycentric Coding Model

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks

Distinguishing rule- and exemplar-based generalization in learning systems

Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error

Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching

Rich Feature Construction for the Optimization-Generalization Dilemma

Task-aware Privacy Preservation for Multi-dimensional Data

TACTiS: Transformer-Attentional Copulas for Time Series

Risk-Averse No-Regret Learning in Online Convex Games

Fourier Learning with Cyclical Data

Adaptive Second Order Coresets for Data-efficient Machine Learning

Describing Differences between Text Distributions with Natural Language

Uncertainty Modeling in Generative Compressed Sensing

Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance

Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework

Parsimonious Learning-Augmented Caching

On the Statistical Benefits of Curriculum Learning

GraphFM: Improving Large-Scale GNN Training via Feature Momentum

NysADMM: faster composite convex optimization via low-rank approximation

Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity

Constrained Offline Policy Optimization

End-to-End Balancing for Causal Continuous Treatment-Effect Estimation

Constrained Discrete Black-Box Optimization using Mixed-Integer Programming

Learning to Solve PDE-constrained Inverse Problems with Graph Networks

Feature and Parameter Selection in Stochastic Linear Bandits

Faster Algorithms for Learning Convex Functions

Optimal Algorithms for Mean Estimation under Local Differential Privacy

Removing Batch Normalization Boosts Adversarial Training

Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions

GALAXY: Graph-based Active Learning at the Extreme

Preconditioning for Scalable Gaussian Process Hyperparameter Optimization

Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points

Implicit Bias of Linear Equivariant Networks

Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times

ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder

The CLRS Algorithmic Reasoning Benchmark

Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction

Training OOD Detectors in their Natural Habitats

Power-Law Escape Rate of SGD

Why the Rich Get Richer? On the Balancedness of Random Partition Models

Validating Causal Inference Methods

Adversarial Vulnerability of Randomized Ensembles

Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out

Achieving Minimax Rates in Pool-Based Batch Active Learning

On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces

Detached Error Feedback for Distributed SGD with Random Sparsification

RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression

Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning

Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits

Weisfeiler-Lehman Meets Gromov-Wasserstein

HyperPrompt: Prompt-based Task-Conditioning of Transformers

Out-of-Distribution Detection with Deep Nearest Neighbors

Bregman Power k-Means for Clustering Exponential Family Data

Bounding the Width of Neural Networks via Coupled Initialization - A Worst Case Analysis

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization

Information Discrepancy in Strategic Learning

Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation

Simultaneous Graph Signal Clustering and Graph Learning

Fair Representation Learning through Implicit Path Alignment

A General Recipe for Likelihood-free Bayesian Optimization

ROCK: Causal Inference Principles for Reasoning about Commonsense Causality

Interactive Correlation Clustering with Existential Cluster Constraints

Adaptive Random Walk Gradient Descent for Decentralized Optimization

Differentiable Top-k Classification Learning

Linear Bandit Algorithms with Sublinear Time Complexity

A query-optimal algorithm for finding counterfactuals

Label Ranking through Nonparametric Regression

Agnostic Learnability of Halfspaces via Logistic Loss

First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations

Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes

Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training

DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck

Generalizing Gaussian Smoothing for Random Search

A Study of Face Obfuscation in ImageNet

Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

Sanity Simulations for Saliency Methods

Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows

Variational Sparse Coding with Learned Thresholding

Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis

Equivariant Diffusion for Molecule Generation in 3D

Loss Function Learning for Domain Generalization by Implicit Gradient

Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images

Contextual Information-Directed Sampling

COLA: Consistent Learning with Opponent-Learning Awareness

Adapting to Mixing Time in Stochastic Optimization with Markovian Data

From data to functa: Your data point is a function and you can treat it like one

Scaling Structured Inference with Randomization

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets

How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective

Learning to Infer Structures of Network Games

Translatotron 2: High-quality direct speech-to-speech translation with voice preservation

Faster Fundamental Graph Algorithms via Learned Predictions

Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows

In defense of dual-encoders for neural ranking

MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection

Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data

Nesterov Accelerated Shuffling Gradient Method for Convex Optimization

What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?

Algorithms for the Communication of Samples

Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses

Nearly Optimal Policy Optimization with Stable at Any Time Guarantee

Analysis of Stochastic Processes through Replay Buffers

Generalized Strategic Classification and the Case of Aligned Incentives

Policy Gradient Method For Robust Reinforcement Learning

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Structure-preserving GANs

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation

Tell me why! Explanations support learning relational and causal structure

A Random Matrix Analysis of Data Stream Clustering: Coping With Limited Memory Resources

A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes

Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning

Towards Coherent and Consistent Use of Entities in Narrative Generation

Certified Neural Network Watermarks with Randomized Smoothing

On the Practicality of Deterministic Epistemic Uncertainty

Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning

On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions

Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower Bounds

Modeling Structure with Undirected Neural Networks

Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime

Inducing Causal Structure for Interpretable Neural Networks

Controlling Conditional Language Models without Catastrophic Forgetting

ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks

A Differential Entropy Estimator for Training Neural Networks

Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval

Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent

Scalable Computation of Causal Bounds

Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them

Tight and Robust Private Mean Estimation with Few Users

Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk

Modeling Irregular Time Series with Continuous Recurrent Units

No-Regret Learning in Time-Varying Zero-Sum Games

Curriculum Reinforcement Learning via Constrained Optimal Transport

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

PAC-Bayesian Bounds on Rate-Efficient Classifiers

Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model

FedScale: Benchmarking Model and System Performance of Federated Learning at Scale

Probabilistic ODE Solutions in Millions of Dimensions

Sequential Covariate Shift Detection Using Classifier Two-Sample Tests

Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization

On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming

FriendlyCore: Practical Differentially Private Aggregation

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests

Robust Kernel Density Estimation with Median-of-Means principle

Evolving Curricula with Regret-Based Environment Design

The Importance of Non-Markovianity in Maximum State Entropy Exploration

Adversarial Masking for Self-Supervised Learning

Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension

Inverse Contextual Bandits: Learning How Behavior Evolves over Time

Adversarial Attacks on Gaussian Process Bandits

Bayesian Nonparametrics for Offline Skill Discovery

PDE-Based Optimal Strategy for Unconstrained Online Learning

Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data

Shuffle Private Linear Contextual Bandits

Universality of Winning Tickets: A Renormalization Group Perspective

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

SDQ: Stochastic Differentiable Quantization with Mixed Precision

Direct Behavior Specification via Constrained Reinforcement Learning

Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots

Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass

Invariant Ancestry Search

Least Squares Estimation using Sketched Data with Heteroskedastic Errors

Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning

Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering

A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs

A Psychological Theory of Explainability

Composing Partial Differential Equations with Physics-Aware Neural Networks

Stochastic Rising Bandits

How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models

Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data

Geometric Multimodal Contrastive Representation Learning

NOMU: Neural Optimization-based Model Uncertainty

Neural-Symbolic Models for Logical Queries on Knowledge Graphs

The Infinite Contextual Graph Markov Model

Federated Learning with Label Distribution Skew via Logits Calibration

RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval

Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling

Deep symbolic regression for recurrence prediction

Kernel Methods for Radial Transformed Compositional Data with Many Zeros

Equivariance versus Augmentation for Spherical Images

Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers

Decomposing Temporal High-Order Interactions via Latent ODEs

Nearly Optimal Catoni’s M-estimator for Infinite Variance

Label-Free Explainability for Unsupervised Models

AutoIP: A United Framework to Integrate Physics into Gaussian Processes

PINs: Progressive Implicit Networks for Multi-Scale Neural Representations

Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers

Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models

Nonlinear Feature Diffusion on Hypergraphs

Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs

Self-supervised Models are Good Teaching Assistants for Vision Transformers

ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases

Delay-Adaptive Step-sizes for Asynchronous Learning

Transfer Learning In Differential Privacy's Hybrid-Model

On the Finite-Time Performance of the Knowledge Gradient Algorithm

Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control

Dynamic Topic Models for Temporal Document Networks

Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits

Variational On-the-Fly Personalization

Re-evaluating Word Mover's Distance

Revisiting the Effects of Stochasticity for Hamiltonian Samplers

Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration

Difference Advantage Estimation for Multi-Agent Policy Gradients

A Joint Exponential Mechanism For Differentially Private Top-$k$

Being Properly Improper

Global Optimization Networks

On the Effects of Artificial Data Modification

Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

Robustness Implies Generalization via Data-Dependent Generalization Bounds

Order Constraints in Optimal Transport

Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing

Safe Exploration for Efficient Policy Evaluation and Comparison

Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning

Residual-Based Sampling for Online Outlier-Robust PCA

Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective

Efficient PAC Learning from the Crowd with Pairwise Comparisons

Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more

Generalized Federated Learning via Sharpness Aware Minimization

NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks

Off-Policy Reinforcement Learning with Delayed Rewards

EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning

Towards understanding how momentum improves generalization in deep learning

One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams

Stochastic Reweighted Gradient Descent

Cooperative Online Learning in Stochastic and Adversarial MDPs

Analyzing and Mitigating Interference in Neural Architecture Search

Convergence of Invariant Graph Networks

Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees

Partial Label Learning via Label Influence Function

Instance Dependent Regret Analysis of Kernelized Bandits

A Theoretical Comparison of Graph Neural Network Extensions

Ripple Attention for Visual Perception with Sub-quadratic Complexity

Offline Meta-Reinforcement Learning with Online Self-Supervision

Prototype Based Classification from Hierarchy to Fairness

Understanding Robust Overfitting of Adversarial Training and Beyond

Fast Provably Robust Decision Trees and Boosting

MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone

Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage

Simple and near-optimal algorithms for hidden stratification and multi-group learning

Function-space Inference with Sparse Implicit Processes

C*-algebra Net: A New Approach Generalizing Neural Network Parameters to C*-algebra

Equivariant Quantum Graph Circuits

Attentional Meta-learners for Few-shot Polythetic Classification

Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks

Nonparametric Embeddings of Sparse High-Order Interaction Events

Robust Models Are More Interpretable Because Attributions Look Normal

Divergence-Regularized Multi-Agent Actor-Critic

Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding

DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning

Generative Trees: Adversarial and Copycat

Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes

Learning Domain Adaptive Object Detection with Probabilistic Teacher

Matching Structure for Dual Learning

Large Batch Experience Replay

Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets

Input Dependent Sparse Gaussian Processes

Sublinear-Time Clustering Oracle for Signed Graphs

Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications

Continuous Control with Action Quantization from Demonstrations

An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees

Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

A Neural Tangent Kernel Perspective of GANs

On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Differentially Private Approximate Quantiles

Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition

Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization

Centroid Approximation for Bootstrap: Improving Particle Quality at Inference

Learning Mixtures of Linear Dynamical Systems

Data-Efficient Double-Win Lottery Tickets from Robust Pre-training

Adaptive Data Analysis with Correlated Observations

$p$-Laplacian Based Graph Neural Networks

Adapting k-means Algorithms for Outliers

Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data

Surrogate Likelihoods for Variational Annealed Importance Sampling

Learning to Hash Robustly, Guaranteed

Bounding Training Data Reconstruction in Private (Deep) Learning

Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances

Bayesian Continuous-Time Tucker Decomposition

Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures

Fairness Interventions as (Dis)Incentives for Strategic Manipulation

Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion

DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting

Learning Stable Classifiers by Transferring Unstable Features

Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning

Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning

Congested Bandits: Optimal Routing via Short-term Resets

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria

A Resilient Distributed Boosting Algorithm

Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation

QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards

SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals

The dynamics of representation learning in shallow, non-linear autoencoders

Bayesian Nonparametric Learning for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot Locations

Structural Entropy Guided Graph Hierarchical Pooling

Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning

Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence

Deep Probability Estimation

SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features

Detecting Corrupted Labels Without Training a Model to Predict

Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning

Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence

Sample Efficient Learning of Predictors that Complement Humans

Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense

From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers

Generating 3D Molecules for Target Protein Binding

Deep and Flexible Graph Neural Architecture Search

Streaming Algorithms for Support-Aware Histograms

Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL

Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems

Optimal Algorithms for Stochastic Multi-Level Compositional Optimization

Off-Policy Evaluation for Large Action Spaces via Embeddings

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training

Learning Bellman Complete Representations for Offline Policy Evaluation

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

GenLabel: Mixup Relabeling using Generative Models

Diversified Adversarial Attacks based on Conjugate Gradient Method

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning

Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models

Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching

Efficient Test-Time Model Adaptation without Forgetting

Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(\epsilon^{-7/4})$ Complexity

CerDEQ: Certifiable Deep Equilibrium Model

PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs

Optimization-Induced Graph Implicit Nonlinear Diffusion

G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters

Auxiliary Learning with Joint Task and Data Scheduling

Adversarial Attack and Defense for Non-Parametric Two-Sample Tests

Self-Supervised Representation Learning via Latent Graph Prediction

Mitigating Neural Network Overconfidence with Logit Normalization

Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets

Robustness and Accuracy Could Be Reconcilable by (Proper) Definition

Online Learning with Knapsacks: the Best of Both Worlds

Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints

UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees

AdaGrad Avoids Saddle Points

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

BabelTower: Learning to Auto-parallelized Program Translation

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

Fast Relative Entropy Coding with A* coding

LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood

Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval

Deep equilibrium networks are sensitive to initialization statistics

Online Algorithms with Multiple Predictions

Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity

Dataset Condensation via Efficient Synthetic-Data Parameterization

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning

Batched Dueling Bandits

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails

From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses

Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning

Gradient Descent on Neurons and its Link to Approximate Second-order Optimization

Toward Compositional Generalization in Object-Oriented World Modeling

C-MinHash: Improving Minwise Hashing with Circulant Permutation

FOCUS: Familiar Objects in Common and Uncommon Settings

Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

(Non-)Convergence Results for Predictive Coding Networks

Monarch: Expressive Structured Matrices for Efficient and Accurate Training

Forget-free Continual Learning with Winning Subnetworks

Constraint-based graph network simulator

OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Online Active Regression

Achieving Fairness at No Utility Cost via Data Reweighing with Influence

Additive Gaussian Processes Revisited

Neural Network Poisson Models for Behavioural and Neural Spike Train Data

Rotting Infinitely Many-Armed Bandits

Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions

Scalable Spike-and-Slab

Active Nearest Neighbor Regression Through Delaunay Refinement

Active Multi-Task Representation Learning

Utility Theory for Sequential Decision Making

Generative Coarse-Graining of Molecular Conformations

Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules

Improving Transformers with Probabilistic Attention Keys

Cross-Space Active Learning on Graph Convolutional Networks

Public Data-Assisted Mirror Descent for Private Model Training

Thompson Sampling for (Combinatorial) Pure Exploration

Greedy when Sure and Conservative when Uncertain about the Opponents

Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images

Online Balanced Experimental Design

Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt

What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?

3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation

TPC: Transformation-Specific Smoothing for Point Cloud Models

Large-Scale Graph Neural Architecture Search

Random Forest Density Estimation

Particle Transformer for Jet Tagging

A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds

Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

Communication-efficient Distributed Learning for Large Batch Optimization

Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework

Metric-Fair Active Learning

Thresholded Lasso Bandit

Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots

Benchmarking and Analyzing Point Cloud Classification under Corruptions

Position Prediction as an Effective Pretraining Strategy

Generalizing to New Physical Systems via Context-Informed Dynamics Model

Multi-Level Branched Regularization for Federated Learning

Efficient Variance Reduction for Meta-learning

ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers

Double Sampling Randomized Smoothing

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

History Compression via Language Models in Reinforcement Learning

Non-Vacuous Generalisation Bounds for Shallow Neural Networks