ICML 2023 Papers

Browse

mini compact detail

Unsupervised Skill Discovery for Learning Shared Structures across Changing Environments

Personalized Federated Learning under Mixture of Distributions

Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces

Improving Fair Training under Correlation Shifts

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

Parallel Online Clustering of Bandits via Hedonic Game

High-dimensional Clustering onto Hamiltonian Cycle

A Generalization of ViT/MLP-Mixer to Graphs

Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning

Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression

Towards Constituting Mathematical Structures for Learning to Optimize

Controlled Differential Equations on Long Sequences via Non-standard Wavelets

On User-Level Private Convex Optimization

Improved Online Learning Algorithms for CTR Prediction in Ad Auctions

Robust and private stochastic linear bandits

Differentiable Tree Operations Promote Compositional Generalization

Differentiable Simulations for Enhanced Sampling of Rare Events

B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning

The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics

Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

Moderately Distributional Exploration for Domain Generalization

Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

On Coresets for Clustering in Small Dimensional Euclidean spaces

Estimating Joint Treatment Effects by Combining Multiple Experiments

Minimal Width for Universal Property of Deep RNN

Weakly Supervised Regression with Interval Targets

Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch

Deep Graph Representation Learning and Optimization for Influence Maximization

DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm

Towards a better understanding of representation dynamics under TD-learning

Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity

The Edge of Orthogonality: A Simple View of What Makes BYOL Tick

Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators

Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization

Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation

Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trains

HOPE: High-order Graph ODE For Modeling Interacting Dynamics

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

The Unreasonable Effectiveness of Few-shot Learning for Machine Translation

On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology

DRew: Dynamically Rewired Message Passing with Delay

Theoretical Bounds on the Network Community Profile from Low-rank Semi-definite Programming

MEWL: Few-shot multimodal word learning with referential uncertainty

Men Also Do Laundry: Multi-Attribute Bias Amplification

Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models

Rethinking Weak Supervision in Helping Contrastive Representation Learning

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation

Alternately Optimized Graph Neural Networks

LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation

PAC Generalization via Invariant Representations

Interpretable Neural-Symbolic Concept Reasoning

Effective Structured Prompting by Meta-Learning and Representative Verbalizer

Uncertainty Estimation by Fisher Information-based Evidential Deep Learning

A Likelihood Approach to Nonparametric Estimation of a Singular Distribution Using Deep Generative Models

The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms

TIDE: Time Derivative Diffusion for Deep Learning on Graphs

Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference

Learning to Boost Training by Periodic Nowcasting Near Future Weights

Multi-Agent Best Arm Identification with Private Communications

Generative Decoding of Visual Stimuli

Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames

Multi-Fidelity Covariance Estimation in the Log-Euclidean Geometry

Scaling Vision Transformers to 22 Billion Parameters

Weakly Supervised Disentangled Generative Causal Representation Learning

On the Relationship Between Explanation and Prediction: A Causal View

Unifying Molecular and Textual Representations via Multi-task Language Modelling

Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework

Quantitative Universal Approximation Bounds for Deep Belief Networks

Neural signature kernels as infinite-width-depth-limits of controlled ResNets

Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature

Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks

Why do Nearest Neighbor Language Models Work?

Learning Hidden Markov Models When the Locations of Missing Observations are Unknown

Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes

Harmonic Neural Networks

On the Effectiveness of Offline RL for Dialogue Response Generation

Modality-Agnostic Variational Compression of Implicit Neural Representations

IncDSI: Incrementally Updatable Document Retrieval

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Do Perceptually Aligned Gradients Imply Robustness?

Towards Understanding Ensemble Distillation in Federated Learning

Fast Rates for Maximum Entropy Exploration

Quantile Credit Assignment

LegendreTron: Uprising Proper Multiclass Loss Learning

Nearly-tight Bounds for Deep Kernel Learning

PAL: Program-aided Language Models

Directed Chain Generative Adversarial Networks

Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond

Motion Question Answering via Modular Motion Programs

Modeling Dynamic Environments with Scene Graph Memory

Adversarial Classification: Necessary Conditions and Geometric Flows

Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits

Proper Losses for Discrete Generative Models

Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks

Enforcing Hard Constraints with Soft Barriers: Safe-driven Reinforcement Learning in Unknown Stochastic Environments

Learning Mixtures of Gaussians with Censored Data

VIMA: Robot Manipulation with Multimodal Prompts

The multimarginal optimal transport formulation of adversarial multiclass classification

Settling the Reward Hypothesis

On Regularization and Inference with Label Constraints

Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching

Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data

Continuous Spatiotemporal Transformer

Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning

Simple and Fast Group Robustness by Automatic Feature Reweighting

Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?

Are Large Kernels Better Teachers than Transformers for ConvNets?

Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model

A/B Testing in Network Data with Covariate-Adaptive Randomization

Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions

Function-Space Regularization in Neural Networks: A Probabilistic Perspective

CogQA: Answering Advanced Questions on Scientific Articles

Toward Large Kernel Models

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach

LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation

HyperTuning: Toward Adapting Large Language Models without Back-propagation

Less is More: Task-aware Layer-wise Distillation for Language Model Compression

Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models

Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise

Von Mises Mixture Distributions for Molecular Conformation Generation

Who Needs to Know? Minimal Knowledge for Optimal Coordination

A General Representation Learning Framework with Generalization Performance Guarantees

MALTS: Matching After Learning to Stretch

Gradient Descent Converges Linearly for Logistic Regression on Separable Data

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Model-based Offline Reinforcement Learning with Count-based Conservatism

Combinatorial Neural Bandits

Semi-Parametric Contextual Pricing Algorithm using Cox Proportional Hazards Model

Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation

MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action

Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings

Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning

Understanding the Role of Feedback in Online Learning with Switching Costs

CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling

Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving

Adaptive Whitening in Neural Populations with Gain-modulating Interneurons

GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency

Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions

A Distributional Optimization-based Framework for Confidence Bounds of Risk Measures

Offline Meta Reinforcement Learning with In-Distribution Online Adaptation

Improved Learning-Augmented Algorithms for the Multi-Option Ski Rental Problem via Best-Possible Competitive Analysis

Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods

Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks

Generative Graph Dictionary Learning

Vector Quantized Wasserstein Auto-Encoder

Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization

Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression

Nonlinear Causal Discovery with Latent Confounders

Traversing Between Modes in Function Space for Fast Ensembling

On the Impact of Knowledge Distillation for Model Interpretability

Towards Trustworthy Explanation: On Causal Rationalization

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

Federated Hypergradient Computation via Aggregated Iterative Differentiation

Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models

Constrained Efficient Global Optimization of Expensive Black-box Functions

Returning The Favour: When Regression Benefits From Probabilistic Causal Knowledge

Image generation with shortest path diffusion

Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability

Exponential Smoothing for Off-Policy Learning

Memory-Based Meta-Learning on Non-Stationary Distributions

Equivariant Architectures for Learning in Deep Weight Spaces

Auxiliary Learning as an Asymmetric Bargaining Game

Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms

Towards Unbiased Training in Federated Open-world Semi-supervised Learning

Double-Weighting for Covariate Shift Adaptation

Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction

A theory of representation learning gives a deep generalisation of kernel methods

Entropy-driven Unsupervised Keypoint Representation Learning in Videos

Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

Reward-Mixing MDPs with Few Contexts are Learnable

Conformalization of Sparse Generalized Linear Models

From Hypergraph Energy Functions to Hypergraph Neural Networks

A Fully First-Order Method for Stochastic Bilevel Optimization

Learning the Dynamics of Sparsely Observed Interacting Systems

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection

Making Transformers Compute-lite for CPU inference

Block subsampled randomized Hadamard transform for Nystr ̈om approximation on distributed architectures

Towards Quantum Machine Learning for Constrained Combinatorial Optimization: a Quantum QAP Solver

On the Robustness of Randomized Ensembles to Adversarial Perturbations

Policy Gradient in Robust MDPs with Global Convergence Guarantee

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

Provably Learning Object-Centric Representations

Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics

Learning Preconditioner for Conjugate Gradient PDE Solvers

Implicit Neural Spatial Representations for Time-dependent PDEs

Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning

Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process

Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning

Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach

Semi-Offline Reinforcement Learning for Optimized Text Generation

Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees

Hierarchical Neural Coding for Controllable CAD Model Generation

A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates

CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks

Discovering Object-Centric Generalized Value Functions From Pixels

FlexGen: High-throughput Generative Inference of Large Language Models with a Single GPU

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Optimizing DDPM Sampling with Shortcut Fine-Tuning

A Universal Unbiased Method for Classification from Aggregate Observations

On Pitfalls of Test-Time Adaptation

Learning Control-Oriented Dynamical Structure from Data

Rotation and Translation Invariant Representation Learning with Implicit Neural Representations

Generalized Reductions: Making any Hierarchical Clustering Fair and Balanced with Low Cost

Expectation-Complete Graph Representations with Homomorphisms

Coupled Variational Autoencoder

Multi-Objective Population Based Training

Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer

Federated Adversarial Learning: A Framework with Convergence Analysis

Federated Online and Bandit Convex Optimization

Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases

High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors

Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data

DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning

Adapting to game trees in zero-sum imperfect information games

Unsupervised Out-of-Distribution Detection with Diffusion Inpainting

Internally Rewarded Reinforcement Learning

Online Platt Scaling with Calibeating

A Kernel-Based View of Language Model Fine-Tuning

Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning

CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis

Shape-Guided Dual-Memory Learning for 3D Anomaly Detection

Towards Theoretical Understanding of Inverse Reinforcement Learning

Refined Regret for Adversarial MDPs with Linear Function Approximation

Stable Estimation of Heterogeneous Treatment Effects

On Generalizations of Some Distance Based Classifiers for HDLSS Data

MixFlows: principled variational inference via mixed flows

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation

Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations

Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

Behavior Contrastive Learning for Unsupervised Skill Discovery

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias

Subequivariant Graph Reinforcement Learning in 3D Environments

In Search for a Generalizable Method for Source Free Domain Adaptation

Multi-Task Off-Policy Learning from Bandit Feedback

Sampling random graph homomorphisms and applications to network data analysis

A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel

Meta-learning Parameterized Skills

Sequential Strategic Screening

Global Context Vision Transformers

On Bridging the Gap between Mean Field and Finite Width in Deep Random Multilayer Perceptron with Batch Normalization

Estimation Beyond Data Reweighting: Kernel Method of Moments

Generalization on the Unseen, Logic Reasoning and Degree Curriculum

Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities

Importance Weighted Variational Bayes for Protein Sequence Design

Contextual Combinatorial Bandits with Probabilistically Triggered Arms

Propensity Matters: Measuring and Enhancing Balancing for Recommendation

All in a Row: Compressed Convolution Networks for Graphs

Reinforcement Learning in Low-rank MDPs with Density Features

InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models

Graph Generative Model for Benchmarking Graph Neural Networks

Causal Isotonic Calibration for Heterogeneous Treatment Effects

The photo-sketch correspondence problem: a new benchmark and a self-supervised approach

Path Neural Networks: Expressive and Accurate Graph Neural Networks

The Catalog Problem: Clustering and Ordering Variable-Sized Sets

A Robust Test for the Stationarity Assumption in Sequential Decision Making

Moccasin: Efficient Tensor Rematerialization for Neural Networks

Variational Sparse Inverse Cholesky Approximation for Latent Gaussian Processes via Double Kullback-Leibler Minimization

Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

Deep Regression Unlearning

Understanding and Generalizing Contrastive Learning from the Inverse Optimal Transport Perspective

ClimaX: A foundation model for weather and climate

What Can Be Learnt With Wide Convolutional Neural Networks?

SinDDM: A Single Image Denoising Diffusion Model

An Effective Meaningful Way to Evaluate Survival Models

Conditional Graph Information Bottleneck for Molecular Relational Learning

Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information

Learning Optimal Group-structured Individualized Treatment Rules with Many Treatments

Global optimality for Euclidean CCCP under Riemannian convexity

DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm

Which Invariance Should We Transfer? A Causal Minimax Learning Approach

MyoDex: A Generalizable Prior for Dexterous Manipulation

On the Training Instability of Shuffling SGD with Batch Normalization

Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation

An Instrumental Variable Approach to Confounded Off-Policy Evaluation

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

FeDXL: Provable Federated Learning for Deep X-Risk Optimization

Effectively Using Public Data in Privacy Preserving Machine Learning

A Nearly-Optimal Bound for Fast Regression with $\ell_\infty$ Guarantee

Multi-channel Autobidding with Budget and ROI Constraints

X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion

Text-To-4D Dynamic Scene Generation

Conditions and Assumptions for Constraint-based Causal Structure Learning

SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient

Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm.

Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes

Can Neural Network Memorization Be Localized?

Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization

Conformal Prediction Sets for Graph Neural Networks

Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations

Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal

SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models

On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

When does Privileged information Explain Away Label Noise?

Revisiting Bellman Errors for Offline Model Selection

Partial Optimality in Cubic Correlation Clustering

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

Self-Repellent Random Walks on General Graphs - Achieving Minimal Sampling Variance via Nonlinear Markov Chains

TabLeak: Tabular Data Leakage in Federated Learning

Online Learning with Feedback Graphs: The True Shape of Regret

A Scalable Frank-Wolfe-Based Algorithm for the Max-Cut SDP

Anchor Sampling for Federated Learning with Partial Client Participation

Markovian Gaussian Process Variational Autoencoders

Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards

General Covariance Data Augmentation for Neural PDE Solvers

From Robustness to Privacy and Back

Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration

The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation

SinFusion: Training Diffusion Models on a Single Image or Video

Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies

Oracles and Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning

Restoration based Generative Models

Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator

The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning

Cut your Losses with Squentropy

Self-supervised learning of Split Invariant Equivariant representations

Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond

IRNeXt: Rethinking Convolutional Network Design for Image Restoration

Meta-learning based Adaptive Stability Certificates in Dynamical Systems

Certifying Ensembles: A General Certification Theory with S-Lipschitzness

Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap

Simplified Temporal Consistency Reinforcement Learning

Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains

PASTA: Pessimistic Assortment Optimization

Functional Neural Networks: Shift invariant models for functional data with applications to EEG classification

Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data

A theory of continuous generative flow networks

Efficient preconditioned stochastic gradient descent for estimation in latent variable models

Set-membership Belief State-based Reinforcement Learning for POMDPs

Efficient Distribution-Free Predictive Inference for Standard and Feedback Covariate Shift

Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion

Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points

Input uncertainty propagation through trained neural networks

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

2D-Shapley: A Framework for Fragmented Data Valuation

DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning

Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime

RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank

RGE: A Repulsive Graph Rectification for Node Classification via Influence

Adaptive Computation with Elastic Input Sequence

A Study on Transformer Configuration and Training Objective

Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA

Correcting discount-factor mismatch in on-policy policy gradient methods

Data Structures for Density Estimation

The Computational Complexity of Concise Hypersphere Classification

Reinforcement Learning from Passive Data via Latent Intentions

Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers

Leveraging Proxy of Training Data for Test-Time Adaptation

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems

Fine-Tuning Language Models via Epistemic Neural Networks

End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization

Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing

FARE: Provably Fair Representation Learning with Practical Certificates

Tighter Information-Theoretic Generalization Bounds from Supersamples

On the Convergence Rate of Gaussianization with Random Rotations

Forget Unlearning: Towards True Data-Deletion in Machine Learning

CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models

Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data

Feature learning in deep classifiers through Intermediate Neural Collapse

Causal Proxy Models for Concept-based Model Explanations

TGRL: Teacher Guided Reinforcement Learning Algorithm

Identification of the Adversary from a Single Adversarial Example

Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods

Dimensionality Reduction for General KDE Mode Finding

Integrating Prior Knowledge in Contrastive Learning with Kernel

MonoFlow: Rethinking Divergence GANs via the Perspective of Differential Equations

Doubly Optimal No-Regret Learning in Monotone Games

Explaining Reinforcement Learning with Shapley Values

A new near-linear time algorithm for k-nearest neighbor search using a compressed cover tree

Rigid body flows for sampling molecular crystal structures

Multi-Task Differential Privacy Under Distribution Skew

Gibbsian Polar Slice Sampling

Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks

Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback

Representer Point Selection for Explaining Regularized High-dimensional Models

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations

Efficient displacement convex optimization with particle gradient descent

The Test of Tests: A Framework for Differentially Private Hypothesis Testing

Spurious Valleys and Clustering Behavior of Neural Networks

Efficient Graph Field Integrators Meet Point Clouds

Fisher Information Embedding for Node and Graph Learning

ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models

Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models

Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least

Bayesian Estimation of Differential Privacy

Adaptive Estimation of Graphical Models under Total Positivity

Disentangled Multi-Fidelity Deep Bayesian Active Learning

Understand and Modularize Generator Optimization in ELECTRA-style Pretraining

Optimistic Planning by Regularized Dynamic Programming

Bayesian Design Principles for Frequentist Sequential Learning

Domain Adaptation for Time Series Under Feature and Label Shifts

Towards Sustainable Learning: Coresets for Data-efficient Deep Learning

On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network

On Data Manifolds Entailed by Structural Causal Models

The Hessian perspective into the Nature of Convolutional Neural Networks

Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations

Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modularized Learning

Learning Belief Representations for Partially Observable Deep RL

MultiAdam: Parameter-wise Scale-invariant Optimizer for Physics-informed Neural Network

Polynomial Preconditioning for Gradient Methods

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

Slot-VAE: Object-Centric Scene Generation with Slot Attention

Internet Explorer: Targeted Representation Learning on the Open Web

Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables

Short-lived High-volume Bandits

Active Policy Improvement from Multiple Black-box Oracles

Mixing Predictions for Online Metric Algorithms

Deep Generative Symbolic Regression with Monte-Carlo-Tree-Search

Approximate Causal Effect Identification under Weak Confounding

DRCFS: Doubly Robust Causal Feature Selection

Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion

Tractable Control for Auto-regressive Language Generation

Open-Vocabulary Universal Image Segmentation with MaskCLIP

A Large-Scale Study of Probabilistic Calibration in Neural Network Regression

Global optimality of Elman-type RNNs in the mean-field regime

Semi-Autoregressive Energy Flows: Towards Determinant-Free Training of Normalizing Flows

When do Minimax-fair Learning and Empirical Risk Minimization Coincide?

Probabilistic Imputation for Time-series Classification with Missing Data

Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees

Multi-Agent Learning from Learners

Characterizing Multicalibration via Property Elicitation

Conformal Prediction with Missing Values

How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding

Subset-Based Instance Optimality in Private Estimation

A Statistical Perspective on Retrieval-Based Models

Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories

On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning

Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data

Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries

When is Realizability Sufficient for Off-Policy Reinforcement Learning?

Bootstrapped Representations in Reinforcement Learning

New metrics and search algorithms for weighted causal DAGs

Exact Inference in High-order Structured Prediction

The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation

Hyperparameters in Reinforcement Learning and How To Tune Them

Identifiability and Generalizability in Constrained Inverse Reinforcement Learning

Optimizing the Collaboration Structure in Cross-Silo Federated Learning

Smart Initial Basis Selection for Linear Programs

Additive Causal Bandits with Unknown Graph

Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning

Resurrecting Recurrent Neural Networks for Long Sequences

Predicting Rare Events by Shrinking Towards Proportional Odds

Efficient Quantum Algorithms for Quantum Optimal Control

SLAMB: Accelerated Large Batch Training with Sparse Communication

High Probability Convergence of Stochastic Gradient Methods

Towards Understanding and Reducing Graph Structural Noise for GNNs

On the Convergence of Gradient Flow on Multi-layer Linear Models

Multi-species multi-task benchmark for learned representations of behavior

Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic

Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels

Maximal Initial Learning Rates in Deep ReLU Networks

Generalized Implicit Follow-The-Regularized-Leader

Algorithms for bounding contribution for histogram estimation under user-level privacy

Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation

One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill

Structural Re-weighting Improves Graph Domain Adaptation

Machine Learning Force Fields with Data Cost Aware Training

ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines

Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions

An SDE for Modeling SAM: Theory and Insights

MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods

Applied Online Algorithms with Heterogeneous Predictors

A Model-Based Method for Minimizing CVaR and Beyond

Extrapolative Controlled Sequence Generation via Iterative Refinement

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video

Protecting Language Generation Models via Invisible Watermarking

Kernel QuantTree

Rethinking Backdoor Attacks

Adversarially Robust PAC Learnability of Real-Valued Functions

Task-specific experimental design for treatment effect estimation

Statistical Indistinguishability of Learning Algorithms

$H$-Consistency Bounds for Pairwise Misranking Loss Surrogates

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

Neural Markov Jump Processes

PFGM++: Unlocking the Potential of Physics-Inspired Generative Models

Parallel neurosymbolic integration with Concordia

Prototype-oriented unsupervised anomaly detection for multivariate time series

Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models

Uncertainty Estimation for Molecules: Desiderata and Methods

Hierarchical Clustering: A Nearly-Optimal Construction for Well-Clustered Graphs

Graphically Structured Diffusion Models

Beam Tree Recursive Cells

User-level Private Stochastic Convex Optimization with Optimal Rates

SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process

Counterfactual Identifiability of Bijective Causal Models

Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems

E$(n)$ Equivariant Message Passing Simplicial Networks

LEVER: Learning to Verify Language-to-Code Generation with Execution

Optimal No-Regret Learning for One-Sided Lipschitz Functions

Partially Observable Multi-agent RL with Provable (Quasi-)Efficiency: Information-Sharing to the Rescue

Neural FIM for learning Fisher information metrics from point cloud data

Variational Mixture of HyperGenerators for Learning Distributions over Functions

Robust Subtask Learning for Compositional Generalization

Strategic Classification with Unknown User Manipulations

Robust and Scalable Bayesian Online Changepoint Detection

Robustly Learning a Single Neuron via Sharpness

Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value

From Adaptive Query Release to Machine Unlearning

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs

Iterative Approximate Cross-Validation

DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design

Inflow, Outflow, and Reciprocity in Machine Learning

Predictive Flows for Faster Ford-Fulkerson

Multisample Flow Matching: Straightening Flows with Minibatch Couplings

Active causal structure learning with advice

Graph Inductive Biases in Transformers without Message Passing

Private Federated Learning with Autotuned Compression

Principled Acceleration of Iterative Numerical Methods Using Machine Learning

Complexity of block coordinate descent with proximal regularization and applications to Wasserstein CP-dictionary learning

Best of Both Worlds Policy Optimization

Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten

Deep Anomaly Detection under Labeling Budget Constraints

On Kinetic Optimal Probability Paths for Generative Models

Off-Policy Average Reward Actor-Critic with Deterministic Policy Search

Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D

Dirichlet Diffusion Score Model for Biological Sequence Generation

NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data

Unit Scaling: Out-of-the-Box Low-Precision Training

Training-Free Neural Active Learning with Initialization-Robustness Guarantees

Learning Rate Schedules in the Presence of Distribution Shift

Approximate Stein Classes for Truncated Density Estimation

Joint Implicit Neural Representations for Global-Scale Species Mapping

Adaptive Coordination in Social Embodied Rearrangement

OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Model

Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning

On Preemption and Learning in Stochastic Scheduling

Linear CNNs Discover the Statistical Structure of the Dataset Using only the Most Dominant Frequencies

Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist

A Model-free Closeness-of-influence Test for Features in Supervised Learning

Can Large Language Models Reason about Program Behavior?

Bayesian Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation of Latent Gaussian Models

Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems

Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?

Exphormer: Sparse Transformers for Graphs

Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization

Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion

Federated Heavy Hitter Recovery under Linear Sketching

Inferring Relational Potentials in Interacting Systems

Conditionally Strongly Log-Concave Generative Models

Toward Efficient Grad-Based Value Estimation

Fast as CHITA: Neural Network Pruning with Combinatorial Optimization

Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup

Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons

Identifying Useful Learnwares for Heterogeneous Label Spaces

Fair Neighbor Embedding

Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces

Bandit Online Linear Optimization with Hints and Queries

Improving $\ell_1$-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints

MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

Test-time Adaptation with Slot-Centric Models

Generative Pretraining for Offline Model-based Optimization

Provable Multi-instance Deep AUC Maximization with Stochastic Pooling

Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization

Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs

Weighted flow diffusion for local graph clustering with node attributes: an algorithm and statistical guarantees

Compressing Tabular Data via Latent Variable Estimation

A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging

Learnability and Algorithm for Continual Learning

Online Local Differential Private Quantile Inference via Self-normalization

H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features

Transformers Learn In-Context by Gradient Descent

The Persistent Laplacian for Data Science: Evaluating Higher-Order Persistent Spectral Representations of Data

DUET: 2D Structured and Approximately Equivariant Representations

Predicting Ordinary Differential Equations with Transformers

BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming

Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss

Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron

Simple Hardware-Efficient Long Convolutions for Sequence Modeling

Specializing Smaller Language Models towards Multi-Step Reasoning

Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates

Feature Programming for Multivariate Time Series Prediction

A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment

PixelAsParam: A Gradient View on Diffusion Sampling with Guidance

Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models

Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning

QAS-Bench: Rethinking Quantum Architecture Search and A Benchmark

Half-Hop: A graph upsampling approach for slowing down message passing

Group Equivariant Fourier Neural Operators for Partial Differential Equations

Near-Optimal Quantum Coreset Construction Algorithms for Clustering

Bilevel Optimization with Coupled Decision-dependent Distributions

Differentially Private Distributed Bayesian Linear Regression with MCMC

InGram: Inductive Knowledge Graph Embedding via Relation Graphs

Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources

On the Initialization of Graph Neural Networks

CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling

A Category-theoretical Meta-analysis of Definitions of Disentanglement

Quantifying the Variability Collapse of Neural Networks

Reinforcement Learning Can Be More Efficient with Multiple Rewards

Robust Explanation for Free or At the Cost of Faithfulness

Jump-Start Reinforcement Learning

Towards Reliable Neural Specifications

Universal Morphology Control via Contextual Modulation

Learning the Right Layers a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs

Provable Benefit of Mixup for Finding Optimal Decision Boundaries

Covariate balancing using the integral probability metric for causal inference

Network Effects in Performative Prediction Games

SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference

The case for 4-bit precision: k-bit Inference Scaling Laws

Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization

Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts

Provable Copyright Protection for Generative Models

Online Restless Bandits with Unobserved States

Analyzing Diffusion as Serial Reproduction

Posterior Sampling for Deep Reinforcement Learning

Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits

Multi-Objective GFlowNets

Linear Causal Disentanglement via Interventions

Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

Cramming: Training a Language Model on a single GPU in one day.

On Computing Optimal Tree Ensembles

Kernel Logistic Regression Approximation of an Understandable ReLU Neural Network

A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems

Learning Compiler Pass Orders using Coreset and Normalized Value Prediction

SGD with large step sizes learns sparse features

Learning Prescriptive ReLU Networks

Achieving Linear Speedup in Non-IID Federated Bilevel Learning

Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning

Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction

Do Machine Learning Models Learn Statistical Rules Inferred from Data?

Blossom: an Anytime Algorithm for Computing Optimal Decision Trees

Generalized Disparate Impact for Configurable Fairness Solutions in ML

Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation

Computational Asymmetries in Robust Classification

Probabilistic Attention-to-Influence Neural Models for Event Sequences

Flash: Concept Drift Adaptation in Federated Learning

Input Perturbation Reduces Exposure Bias in Diffusion Models

NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition

Differentially Private Sharpness-Aware Training

Monotonic Location Attention for Length Generalization

Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals

PaLM-E: An Embodied Multimodal Language Model

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

Self-Interpretable Time Series Prediction with Counterfactual Explanations

Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP

Sketch-Flip-Merge: Mergeable Sketches for Private Distinct Count

DiscoBAX - Discovery of optimal intervention sets in genomic experiment design

UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers

Nonparametric Extensions of Randomized Response for Private Confidence Sets

Optimization for Amortized Inverse Problems

Second-Order Optimization with Lazy Hessians

A Kernelized Stein Discrepancy for Biological Sequences

Streaming Submodular Maximization with Differential Privacy

What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective

Retrosynthetic Planning with Dual Value Networks

Diffusion Models are Minimax Optimal Distribution Estimators

MultiresNet: Sequence Modeling with Multiresolution Convolutional Memory

Collaborative Causal Inference with Fair Incentives

Performative Reinforcement Learning

Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input

GuardHFL: Privacy Guardian for Heterogeneous Federated Learning

Overcoming Simplicity Bias in Deep Networks using a Feature Sieve

Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks

The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning

The Wisdom of Hindsight Makes Language Models Better Instruction Followers

STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition

Speeding Up Bellman Ford via Minimum Violation Permutations

SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot

Efficient RL via Disentangled Environment and Agent Representations

Reflected Diffusion Models

How much does Initialization Affect Generalization?

Context Consistency Regularization for Label Sparsity in Time Series

Constrained Monotonic Neural Networks

Attributing Image Generative Models using Latent Fingerprints

Principled Offline RL in the Presence of Rich Exogenous Information

Multicalibration as Boosting for Regression

Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models

Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation

Statistical Foundations of Prior-Data Fitted Networks

Anti-Exploration by Random Network Distillation

Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective

Certified Robust Neural Networks: Generalization and Corruption Resistance

NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation

Data Poisoning Attacks Against Multimodal Encoders

Kernel Sufficient Dimension Reduction and Variable Selection for Compositional Data via Amalgamation

Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization

MANSA: Learning Fast and Slow in Multi-Agent Systems

Causal Discovery with Latent Confounders Based on Higher-Order Cumulants

Data Representations' Study of Latent Image Manifolds

Contextual Conservative Interleaving Bandits

Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation

FAENet: Frame Averaging Equivariant GNNs for Materials Modeling

Active Learning based Structural Inference

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge

Effective and Efficient Structural Inference with Reservoir Computing

Fractional Denoising for 3D Molecular Pre-training

A Reinforcement Learning Framework for Dynamic Mediation Analysis

On the Functional Similarity of Robust and Non-Robust Neural Representations

Generalization Bounds using Data-Dependent Fractal Dimensions

Learn to Accumulate Evidence from All Training Samples: Theory and Practice

Multi-agent Online Scheduling: MMS Allocations for Indivisible Items

High Fidelity Image Counterfactuals with Probabilistic Causal Models

Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning

Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data

Continual Task Allocation in Meta-Policy Network via Sparse Prompting

Causal Modeling of Policy Interventions From Sequences of Treatments and Outcomes using Gaussian Processes

Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic

UMD: Unsupervised Model Detection for X2X Backdoor Attacks

Extrapolated Random Tree for Regression

Hierarchies of Reward Machines

Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning

Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs

Federated Linear Contextual Bandits with User-level Differential Privacy

Geometric Clifford Algebra Networks

Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows

Accelerated Stochastic Optimization Methods under Quasar-convexity

N$\text{A}^\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning

State and parameter learning with PARIS particle Gibbs

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Tuning Computer Vision Models With Task Rewards

Under-Counted Tensor Completion with Neural Incorporation of Attributes

Weighted Sampling without Replacement for Deep Top-$k$ Classification

Online Mechanism Design for Information Acquisition

LM-Design: Structure-informed Language Models Are Protein Designers

Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

Go Beyond Imagination: Maximizing Episodic Reachability with World Models

Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments

Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series

Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation

A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining

Causal Bounds in Quasi-Markovian Graphs

Delay-agnostic Asynchronous Coordinate Update Algorithm

FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization

Lifelong Language Pretraining with Distribution-Specialized Experts

A Picture of the Space of Typical Learnable Tasks

Hyena Hierarchy: Towards Larger Convolutional Language Models

Transformers as Algorithms: Generalization and Stability in In-context Learning

GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration

Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning

Neural Status Registers

Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction

Improving Adversarial Robustness Through the Contrastive-Guided Diffusion Process

Linkless Link Prediction via Relational Distillation

FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks

Subset Selection Based On Multiple Rankings in the Presence of Bias: Effectiveness of Fairness Constraints for Multiwinner Voting Score Functions

Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making

Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network

Bag of Tricks for Training Data Extraction from Language Models

Comparison of meta-learners for estimating multi-valued treatment heterogeneous effects

One-Step Estimator for Permuted Sparse Recovery

Structured Cooperative Learning with Graphical Model Priors

A Mathematical Model for Curriculum Learning for Parities

Guiding Pretraining in Reinforcement Learning with Large Language Models

Learning Perturbations to Explain Time Series Predictions

Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement

Training Normalizing Flows from Dependent Data

The Power of Uniform Sampling for k-Median

Towards Explaining Distribution Shifts

Direct Parameterization of Lipschitz-Bounded Deep Networks

Generated Graph Detection

Adaptive Smoothing Gradient Learning for Spiking Neural Networks

Pre-training for Speech Translation: CTC Meets Optimal Transport

Out-of-Domain Robustness via Targeted Augmentations

Constrained Causal Bayesian Optimization

Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time

A Theoretical Analysis of the Learning Dynamics under Class Imbalance

Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling

Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics

Towards Practical Preferential Bayesian Optimization with Skew Gaussian Processes

What can online reinforcement learning with function approximation benefit from general coverage conditions?

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization

Emergence of Sparse Representations from Noise

Non-stationary Reinforcement Learning under General Function Approximation

MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL

SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification

Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models

Convergence of first-order methods for nonconvex constrained optimization with dependent data

Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning

Graph Neural Networks with Learnable and Optimal Polynomial Bases

Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian

Learning to Maximize Mutual Information for Dynamic Feature Selection

Emergent Agentic Transformer from Chain of Hindsight Experience

Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization

The Saddle-Point Method in Differential Privacy

From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders

GOAT: A Global Transformer on Large-scale Graphs

Learning to Initiate and Reason in Event-Driven Cascading Processes

Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.

Scaling Laws for Generative Mixed-Modal Language Models

Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback

Temporally Consistent Transformers for Video Generation

Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering

Large Language Models Can Be Easily Distracted by Irrelevant Context

Identifiability of Label Noise Transition Matrix

Proper Scoring Rules for Survival Analysis

Efficient List-Decodable Regression using Batches

Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation

Instrumental Variable Estimation of Average Partial Causal Effects

One-sided Matrix Completion from Two Observations Per Row

How Bad is Top-$K$ Recommendation under Competing Content Creators?

Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models

Stabilizing GANs' Training with Brownian Motion Controller

Featured Graph Coarsening with Similarity Guarantees

Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies

Policy Regularization with Dataset Constraint for Offline Reinforcement Learning

R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents

Lower Bounds for Learning in Revealing POMDPs

Width and Depth Limits Commute in Residual Networks

Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path

Hiding Data Helps: On the Benefits of Masking for Sparse Coding

Streaming Active Learning with Deep Neural Networks

Multiply Robust Off-policy Evaluation and Learning under Truncation by Death

Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation

Data Feedback Loops: Model-driven Amplification of Dataset Biases

Meta-Learning the Inductive Bias of Simple Neural Circuits

Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data

Provable Reset-free Reinforcement Learning by No-Regret Reduction

Mimetic Initialization of Self-Attention Layers

Individually Fair Learning with One-Sided Feedback

Uncertain Evidence in Probabilistic Models and Stochastic Simulators

Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability

On the Impact of Algorithmic Recourse on Social Segregation

Beyond Uniform Lipschitz Condition in Differentially Private Optimization

SurCo: Learning SURrogate costs for COmbinatorial Nonlinear Optimization Problems

Towards a Persistence Diagram that is Robust to Noise and Varied Densities

Stochastic Gradient Succeeds for Bandits

Whose Opinions Do Language Models Reflect?

Optimal Sets and Solution Paths of ReLU Networks

Transformed Distribution Matching for Missing Value Imputation

Understanding Oversquashing in GNNs through the Lens of Effective Resistance

Fast Rates in Time-Varying Strongly Monotone Games

Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization

Tighter Analysis for ProxSkip

On Distribution Dependent Sub-Logarithmic Query Time of Learned Indexing

Atari-5: Distilling the Arcade Learning Environment down to Five Games

Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning

Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits

Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition

Graph Reinforcement Learning for Network Control via Bi-Level Optimization

General Sequential Episodic Memory Model

What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?

System identification of neural systems: If we got it right, would we know?

Cross-Modal Fine-Tuning: Align then Refine

Gradient-based Wang--Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space

Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation

Brainformers: Trading Simplicity for Efficiency

Learning to Bid in Repeated First-Price Auctions with Budgets

Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies

Infinite Action Contextual Bandits with Reusable Data Exhaust

Dropout Reduces Underfitting

D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching

Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling

Target-based Surrogates for Stochastic Optimization

On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline

Investigating the Role of Model-Based Learning in Exploration and Transfer

MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation

On the Convergence of Federated Averaging with Cyclic Client Participation

Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory

Sketched Ridgeless Linear Regression: The Role of Downsampling

Does Sparsity Help in Learning Misspecified Linear Bandits?

Randomized Schur Complement Views for Graph Contrastive Learning

Improved Algorithms for White-Box Adversarial Streams

Exploring the Benefits of Training Expert Language Models over Instruction Tuning

Trompt: Towards a Better Deep Neural Network for Tabular Data

GREAD: Graph Neural Reaction-Diffusion Networks

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization

Active Ranking of Experts Based on their Performances in Many Tasks

Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

Distributional Offline Policy Evaluation with Predictive Error Guarantees

MODeL: Memory Optimizations for Deep Learning

Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization

Learning Mixtures of Markov Chains and MDPs

Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

Mixture Proportion Estimation Beyond Irreducibility

Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute

Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models

Autoregressive Diffusion Model for Graph Generation

Poisoning Generative Replay in Continual Learning to Promote Forgetting

Learning Globally Smooth Functions on Manifolds

Tight Data Access Bounds for Private Top-$k$ Selection

Understanding Plasticity in Neural Networks

When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced Representations

Magneto: A Foundation Transformer

GNOT: A General Neural Operator Transformer for Operator Learning

A Three-regime Model of Network Pruning

Last Switch Dependent Bandits with Monotone Payoff Functions

Inverse Reinforcement Learning without Reinforcement Learning

Topological Point Cloud Clustering

An Information-Theoretic Analysis of Nonstationary Bandit Learning

On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures

Addressing Budget Allocation and Revenue Allocation in Data Market Environment Using an Adaptive Sampling Algorithm

Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition

Achieving Hierarchy-Free Approximation for Bilevel Programs with Equilibrium Constraints

On Penalty-based Bilevel Gradient Descent Method

Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders

GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks

Matrix Estimation for Individual Fairness

Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes

Eventual Discounting Temporal Logic Counterfactual Experience Replay

Competitive Gradient Optimization

Better Diffusion Models Further Improve Adversarial Training

DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models

Automatically Auditing Large Language Models via Discrete Optimization

Data-Copying in Generative Models: A Formal Framework

Graph Contrastive Backdoor Attacks

Provable Data Subset Selection For Efficient Neural Networks Training

On the Stepwise Nature of Self-Supervised Learning

Estimating Causal Effects using a Multi-task Deep Ensemble

Coordinate Descent Methods for Fractional Minimization

Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation

Incentivizing Exploration with Linear Contexts and Combinatorial Actions

Proximal Causal Learning of Conditional Average Treatment Effects

SAM operates far from home: eigenvalue regularization as a dynamical phenomenon

Approximation Algorithms for Fair Range Clustering

Towards Understanding and Improving GFlowNet Training

Gradient-Free Structured Pruning with Unlabeled Data

Coder Reviewer Reranking for Code Generation

A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer

Benign Overfitting in Deep Neural Networks under Lazy Training

Dataset Distillation with Convexified Implicit Gradients

Omnipredictors for Constrained Optimization

Recasting Self-Attention with Holographic Reduced Representations

Gaussian processes at the Helm(holtz): A more fluid model for ocean currents

Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions

Hindsight Learning for MDPs with Exogenous Inputs

Model Transferability with Responsive Decision Subjects

Delving into Noisy Label Detection with Clean Data

GC-Flow: A Graph-Based Flow Network for Effective Clustering

Nonparametric Density Estimation under Distribution Drift

Global Selection of Contrastive Batches via Optimization on Sample Permutations

Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning

On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation

Abstracting Imperfect Information Away from Two-Player Zero-Sum Games

Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes

Disentangled Generative Models for Robust Prediction of System Dynamics

Curious Replay for Model-based Adaptation

Deep Latent State Space Models for Time-Series Generation

Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

Improving Bi-level Optimization Based Methods with Inspiration from Humans' Classroom Study Techniques

Linear optimal partial transport embedding

Quantum Speedups for Zero-Sum Games via Improved Dynamic Gibbs Sampling

Probabilistic Categorical Adversarial Attack and Adversarial Training

Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs

Neural Algorithmic Reasoning with Causal Regularisation

Adversarial Learning of Distributional Reinforcement Learning

Robust Speech Recognition via Large-Scale Weak Supervision

Sequential Monte Carlo Learning for Time Series Structure Discovery

Sample Complexity of Probability Divergences under Group Symmetry

Adversarial Policies Beat Superhuman Go AIs

Sequential Counterfactual Risk Minimization

Automatic Data Augmentation via Invariance-Constrained Learning

Concurrent Shuffle Differential Privacy Under Continual Observation

On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization

Decoding Layer Saliency in Transformers

CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations

Fully Dynamic Submodular Maximization over Matroids

Beyond In-Domain Scenarios: Robust Density-Aware Calibration

A Watermark for Large Language Models

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs

The Benefits of Model-Based Generalization in Reinforcement Learning

Provably and Practically Efficient Neural Contextual Bandits

Training Deep Surrogate Models with Large Scale Online Learning

STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning

Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts

Learning to Design Analog Circuits to Meet Threshold Specifications

Distributed Linear Bandits under Communication Constraints

Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences

On the Expressive Power of Geometric Graph Neural Networks

Geometric Latent Diffusion Models for 3D Molecule Generation

Private Statistical Estimation of Many Quantiles

Improving Graph Generation by Restricting Graph Bandwidth

On the Estimation of Gaussian Mixture Copula Models

Solving Linear Program with Fast Online Learning Algorithms

Paging with Succinct Predictions

Variational Open-Domain Question Answering

Phase Transitions in the Detection of Correlated Databases

Algorithmic Collective Action in Machine Learning

Adversarial Cheap Talk

RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents

Scalable Safe Policy Improvement via Monte Carlo Tree Search

Regularization-free Diffeomorphic Temporal Alignment Nets

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models

Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models

PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation

Constrained Decision Transformer for Offline Safe Reinforcement Learning

A Two-Stage Active Learning Algorithm for k-Nearest Neighbors

Delayed Bandits: When Do Intermediate Observations Help?

Consistency Models

Dynamic IMLE for Few-shot Pretraining-free Generative Modelling

Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

On the Convergence of SARSA with Linear Function Approximation

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

Diffusion Based Representation Learning

Pretraining Language Models with Human Preferences

Optimal randomized multilevel Monte Carlo for repeatedly nested expectations

PAC Prediction Sets for Large Language Models of Code

Scalable Adaptive Computation for Iterative Generation

PAC-Bayesian Offline Contextual Bandits With Guarantees

Special Properties of Gradient Descent with Large Learning Rates

The Power of Learned Locally Linear Models for Nonlinear Policy Optimization

Statistical Learning under Heterogenous Distribution Shift

Intrinsic Sliced Wasserstein Distances for Comparing Collections of Probability Distributions on Manifolds and Graphs

Compositional Score Modeling for Simulation-Based Inference

Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural Networks

Human-Timescale Adaptation in an Open-Ended Task Space

Sequential Predictive Conformal Inference for Time Series

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

Revisiting Structured Variational Autoencoders

Can Forward Gradient Match Backpropagation?

TRAK: Understanding Model Predictions at Scale

Differentially Private Optimization on Large Model at Small Cost

OCD: Learning to Overfit with Conditional Diffusion Models

Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis

The Numerical Stability of Hyperbolic Representation Learning

$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation

Improved Active Multi-Task Representation Learning via Lasso

Multi-task Representation Learning for Pure Exploration in Linear Bandits

Implicit Graph Neural Networks: A Monotone Operator Viewpoint

Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality

Regularizing Towards Soft Equivariance Under Mixed Symmetries

RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations

Image Restoration with Mean-Reverting Stochastic Differential Equations

Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape

Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models

Sequential Kernelized Independence Testing

Differentiable and Transportable Structure Learning

ILLUME: Rationalizing Vision-Language Models through Human Interactions

Flexible Phase Dynamics for Bio-plausible Contrastive Learning

Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.

Demystifying Disagreement-on-the-Line in High Dimensions

Trustworthy Policy Learning under the Counterfactual No-Harm Criterion

Unconstrained Online Learning with Unbounded Losses

Thompson Sampling with Diffusion Generative Prior

Distilling Internet-Scale Vision-Language Models into Embodied Agents

Explainable Data-Driven Optimization: From Context to Decision and Back Again

Fast Online Node Labeling for Very Large Graphs

ContraBAR: Contrastive Bayes-Adaptive Deep RL

Learning useful representations for shifting tasks and distributions

Computational Doob h-transforms for Online Filtering of Discretely Observed Diffusions

XTab: Cross-table Pretraining for Tabular Transformers

Beyond Reward: Offline Preference-guided Policy Optimization

On Many-Actions Policy Gradient

The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond

Shapley Based Residual Decomposition for Instance Analysis

Relevant Walk Search for Explaining Graph Neural Networks

Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits

Temporal Label Smoothing for Early Event Prediction

VectorMapNet: End-to-end Vectorized HD Map Learning

Estimating the Contamination Factor's Distribution in Unsupervised Anomaly Detection

When Personalization Harms Performance: Reconsidering the Use of Group Attributes in Prediction

Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints

Ewald-based Long-Range Message Passing for Molecular Graphs

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning

Cell-Free Latent Go-Explore

Unlocking Slot Attention by Changing Optimal Transport Costs

Alternating Local Enumeration (TnALE): Solving Tensor Network Structure Search with Fewer Evaluations

Generalized Polyak Step Size for First Order Optimization with Momentum

Towards Understanding the Generalization of Graph Neural Networks

Projected Tensor Power Method for Hypergraph Community Recovery

Graph Neural Tangent Kernel: Convergence on Large Graphs

Aligning Language Models with Preferences through $f$-divergence Minimization

Speed-Oblivious Online Scheduling: Knowing (Precise) Speeds is not Necessary

Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning

Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks

Towards Understanding Generalization of Macro-AUC in Multi-label Learning

On the Within-Group Fairness of Screening Classifiers

Causal Structure Learning for Latent Intervened Non-stationary Data

Neural Inverse Operators for Solving PDE Inverse Problems

From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks

How to address monotonicity for model risk management?

On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness

On the Complexity of Bayesian Generalization

Vertical Federated Graph Neural Network for Recommender System

What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings

SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance

Finding Generalization Measures by Contrasting Signal and Noise

Regression with Sensor Data Containing Incomplete Observations

Detecting Out-of-distribution Data through In-distribution Class Prior

DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule

Generalizing Neural Wave Functions

Information-Theoretic State Space Model for Multi-View Reinforcement Learning

Continuation Path Learning for Homotopy Optimization

Fourmer: An Efficient Global Modeling Paradigm for Image Restoration

Multi-Modal Classifiers for Open-Vocabulary Object Detection

Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal

Adversarial Collaborative Learning on Non-IID Features

Provably Invariant Learning without Domain Information

GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets

Denoising MCMC for Accelerating Diffusion-Based Generative Models

Continual Learning in Linear Classification on Separable Data

Total Variation Graph Neural Networks

Learning Control by Iterative Inversion

Calibrating Multimodal Learning

Topological Singularity Detection at Multiple Scales

Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs

Homomorphism AutoEncoder --- Learning Group Structured Representations from Observed Transitions

Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning

Dynamical Linear Bandits

Symmetry-Aware Robot Design with Structured Subgroups

Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

One-Shot Federated Conformal Prediction

Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits

Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents

Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments

Controllability-Aware Unsupervised Skill Discovery

Multiplier Bootstrap-based Exploration

CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets

Towards credible visual model interpretation with path attribution

Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization

Diffusion Models for Offline Black-Box Optimization

Interactive Object Placement with Reinforcement Learning

Mechanistic Mode Connectivity

Contrastive Learning Meets Homophily: Two Birds with One Stone

Adversarial Parameter Attack on Deep Neural Networks

Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning

NeuralSlice: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes

Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression

Leveraging Offline Data in Online Reinforcement Learning

Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization

Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space

Naive imputation implicitly regularizes high-dimensional linear models

Meta Optimal Transport

Hyperbolic Image-text Representations

Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise?

Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction

NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation

A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification

Regret-Minimizing Double Oracle for Extensive-Form Games

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication

Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions

Efficient Sequence Transduction by Jointly Predicting Tokens and Durations

Buying Information for Stochastic Optimization

Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits

Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems

Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation

Federated Conformal Predictors for Distributed Uncertainty Quantification

Learning in POMDPs is Sample-Efficient with Hindsight Observability

MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose

Sharper Bounds for $\ell_p$ Sensitivity Sampling

Multi-Environment Pretraining Enables Transfer to Action Limited Datasets

Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming

Latent Traversals in Generative Models as Potential Flows

Taxonomy-Structured Domain Adaptation

Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection

A New PHO-rmula for Improved Performance of Semi-Structured Networks

A Flexible Diffusion Model

On Sampling with Approximate Transport Maps

COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects

On the Occupancy Measure of Non-Markovian Policies in Continuous MDPs

How Jellyfish Characterise Alternating Group Equivariant Neural Networks

ODS: Test-Time Adaptation in the Presence of Open-World Data Shift

Differentiable Multi-Target Causal Bayesian Experimental Design

Fair yet Asymptotically Equal Collaborative Learning

From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning

Safe Offline Reinforcement Learning with Real-Time Budget Constraints

Simplex Random Features

Differential Privacy has Bounded Impact on Fairness in Classification

The Role of Entropy and Reconstruction for Multi-View Self-Supervised Learning

SlotGAT: Slot-based Message Passing for Heterogeneous Graphs

Generating Private Synthetic Data with Genetic Algorithms

Hierarchical Diffusion for Offline Decision Making

A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning

LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control

Fast Excess Risk Rates via Offset Rademacher Complexity

Doubly Adversarial Federated Bandits

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

AudioLDM: Text-to-Audio Generation with Latent Diffusion Models

Cooperative Open-ended Learning Framework for Zero-Shot Coordination

Stochastic Gradient Descent under Markov-Chain Sampling Schemes

Learning Instance-Specific Augmentations by Capturing Local Invariances

Sampling-based Nyström Approximation and Kernel Quadrature

Achieving High Accuracy with PINNs via Energy Natural Gradient Descent

Graph Switching Dynamical Systems

Boosting Graph Contrastive Learning via Graph Contrastive Saliency

Bigger, Better, Faster: Human-level Atari with human-level efficiency

Nonparametric Iterative Machine Teaching

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning

HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models

Understanding Self-Predictive Learning for Reinforcement Learning

VA-learning as a more efficient alternative to Q-learning

CRISP: Curriculum based Sequential neural decoders for Polar code family

Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals

On Uni-Modal Feature Learning in Supervised Multi-Modal Learning

Revisiting Weighted Aggregation in Federated Learning with Neural Networks

Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games

SRATTA: Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning.

Statistical Inference on Multi-armed Bandits with Delayed Feedback

StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes

SAAL: Sharpness-Aware Active Learning

Towards Deep Attention in Graph Neural Networks: Problems and Remedies

Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule

Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy

Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks

Approximately Optimal Core Shapes for Tensor Decompositions

Understanding the Impact of Adversarial Robustness on Accuracy Disparity

Improved Online Conformal Prediction via Strongly Adaptive Online Learning

Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes

Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano

Fast Combinatorial Algorithms for Min Max Correlation Clustering

Grounding Language Models to Images for Multimodal Inputs and Outputs

GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series

Scaling Laws for Reward Model Overoptimization

SE(3) diffusion model with application to protein backbone generation

On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters

Graph Mixup with Soft Alignments

Transformers Meet Directed Graphs

Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features

The Fast Johnson-Lindenstrauss Transform Is Even Faster

Normalizing Flows for Interventional Density Estimation

BEATs: Audio Pre-Training with Acoustic Tokenizers

Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction

GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations

Learning Distributions over Quantum Measurement Outcomes

DDGR: Continual Learning with Deep Diffusion-based Generative Replay

Efficiently predicting high resolution mass spectra with graph neural networks

Model-Aware Contrastive Learning: Towards Escaping the Dilemmas

ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction

Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets

Wasserstein Barycenter Matching for Graph Size Generalization of Message Passing Neural Networks

OpenFE: Automated Feature Generation with Expert-level Performance

Random Grid Neural Processes for Parametric Partial Differential Equations

On the Identifiability and Estimation of Causal Location-Scale Noise Models

ModelDiff: A Framework for Comparing Learning Algorithms

Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances

GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks

Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator

End-to-End Full-Atom Antibody Design

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

Personalized Federated Learning with Inferred Collaboration Graphs

Progressive Purification for Instance-Dependent Partial Label Learning

SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning

Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models

FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning

Fast Private Kernel Density Estimation via Locality Sensitive Quantization

FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction

Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction

Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled Representations

Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis

Bayesian online change point detection with Hilbert space approximate Student-t process

Graph Positional Encoding via Random Feature Propagation

Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity

Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations

Robust Satisficing MDPs

Learning to Optimize Differentiable Games

A Closer Look at the Intervention Procedure of Concept Bottleneck Models

Regression with Label Permutation in Generalized Linear Model

Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning

A Coupled Flow Approach to Imitation Learning

Reliable Measures of Spread in High Dimensional Latent Spaces

Adaptive Annealed Importance Sampling with Constant Rate Progress

Large Language Models Struggle to Learn Long-Tail Knowledge

Neural Diffusion Processes

Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation

Target-Aware Generative Augmentations for Single-Shot Adaptation

On Heterogeneous Treatment Effects in Heterogeneous Causal Graphs

Dynamics-inspired Neuromorphic Visual Representation Learning

On the Power of Foundation Models

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score

InfoOT: Information Maximizing Optimal Transport

On the Connection Between MPNN and Graph Transformer

Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing

Interval Bound Interpolation for Few-shot Learning with Few Tasks

Are Equivariant Equilibrium Approximators Beneficial?

ChiPFormer: Transferable Chip Placement via Offline Decision Transformer

MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement

Complementary Attention for Multi-Agent Reinforcement Learning

Simple MViT: A Hierarchical Vision Transformer without the Bells-and-Whistles

Explaining the effects of non-convergent MCMC in the training of Energy-Based Models

Interpolation for Robust Learning: Data Augmentation on Geodesics

Nearly Optimal Competitive Ratio for Online Allocation Problems with Two-sided Resource Constraints and Finite Requests

Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting

Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning

A Kernel Stein Test of Goodness of Fit for Sequential Models

I$^2$SB: Image-to-Image Schrödinger Bridge

Continual Vision-Language Representation Learning with Off-Diagonal Information

Memory-Based Dual Gaussian Processes for Sequential Learning

Faster Rates of Convergence to Stationary Points in Differentially Private Optimization

AdaBoost is not an Optimal Weak to Strong Learner

Differentially Private Stochastic Convex Optimization under a Quantile Loss Function

Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction

Learning Affinity with Hyperbolic Representation for Spatial Propagation

Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models

Bootstrap in High Dimension with Low Computation

Synthetic data for model selection

Quantum Lower Bounds for Finding Stationary Points of Nonconvex Functions

Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure

For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal

BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models

SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Defects of Convolutional Decoder Networks in Frequency Representation

Exploring Chemical Space with Score-based Out-of-distribution Generation

Concept-based Explanations for Out-of-Distribution Detectors

Reparameterized Policy Learning for Multimodal Trajectory Optimization

Optimal Shrinkage for Distributed Second-Order Optimization

Towards Robust Graph Incremental Learning on Evolving Graphs

Not all Strongly Rayleigh Distributions Have Small Probabilistic Generating Circuits

Nugget: Neural Agglomerative Embeddings of Text

Automatically marginalized MCMC in probabilistic programming

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

Neural networks trained with SGD learn distributions of increasing complexity

Regret Minimization and Convergence to Equilibria in General-sum Markov Games

Learning to Decouple Complex Systems

Prompting Large Language Model for Machine Translation: A Case Study

Non-autoregressive Conditional Diffusion Models for Time Series Prediction

FedDisco: Federated Learning with Discrepancy-Aware Collaboration

Enabling First-Order Gradient-Based Learning for Equilibrium Computation in Markets

SpeedDETR: Speed-aware Transformers for End-to-end Object Detection

Local Vertex Colouring Graph Neural Networks

CLIPood: Generalizing CLIP to Out-of-Distributions

Metagenomic Binning using Connectivity-constrained Variational Autoencoders

Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds

Scaling of Class-wise Training Losses for Post-hoc Calibration

Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field Perspective

A Law of Robustness beyond Isoperimetry

Tight and fast generalization error bound of graph embedding in metric space.

ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation

No One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server Computation

Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs

Generalization Analysis for Contrastive Representation Learning

Gaussian Process Priors for Systems of Linear Partial Differential Equations with Constant Coefficients

Understanding Backdoor Attacks through the Adaptability Hypothesis

Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice

Continual Learners are Incremental Model Generalizers

LinSATNet: The Positive Linear Satisfiability Neural Networks

Optimal Arms Identification with Knapsacks

DIVISION: Memory Efficient Training via Dual Activation Precision

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation

The Ideal Continual Learner: An Agent That Never Forgets

TIPS: Topologically Important Path Sampling for Anytime Neural Networks

Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability

Exploring Model Dynamics for Accumulative Poisoning Discovery

Muse: Text-To-Image Generation via Masked Generative Transformers

Delayed Feedback in Kernel Bandits

FaDIn: Fast Discretized Inference for Hawkes Processes with General Parametric Kernels

Is Learning Summary Statistics Necessary for Likelihood-free Inference?

FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems

ClusterFuG: Clustering Fully connected Graphs by Multicut

A unified optimization framework of ANN-SNN Conversion: towards optimal mapping from activation values to firing rates

PFNs4BO: Meta-Learning the surrogate model for Bayesian optimization from scratch using Transformers

Improving the Model Consistency of Decentralized Federated Learning

Implicit Jacobian regularization weighted with impurity of probability output

Dink-Net: Neural Clustering on Large Graphs

Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes

Improving Visual Prompt Tuning for Self-supervised Vision Transformers

Online Prototype Alignment for Few-shot Policy Transfer

Probabilistic Concept Bottleneck Models

Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning

Geometric Autoencoders - What You See is What You Decode

Robust Camera Pose Refinement for Multi-Resolution Hash Encoding

Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization

Competing for Shareable Arms in Multi-Player Multi-Armed Bandits

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Estimating Possible Causal Effects with Latent Variables via Adjustment

Bit Allocation using Optimization

Solving High-Dimensional PDEs with Latent Spectral Models

Oscillation-free Quantization for Low-bit Vision Transformers

FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization

Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance

Robust Perception through Equivariance

Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling

On the Optimality of Misspecified Kernel Ridge Regression

Multi-View Masked World Models for Visual Robotic Manipulation

Performative Recommendation: Diversifying Content via Strategic Incentives

How Does Information Bottleneck Help Deep Learning?

Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks

Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise

Towards Controlled Data Augmentations for Active Learning

Bi-directional Masks for Efficient N:M Sparse Training

Margin-based Neural Network Watermarking

Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement

Opponent-Limited Online Search for Imperfect Information Games

Pruning via Sparsity-indexed ODE: a Continuous Sparsity Viewpoint

Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization

Revisiting Discriminative vs. Generative Classifiers: Theory and Implications

Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning

Long Horizon Temperature Scaling

Robust Weak Supervision with Variational Auto-Encoders

Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy

Task-Specific Skill Localization in Fine-tuned Language Models

Near-Optimal $\Phi$-Regret Learning in Extensive-Form Games

Which Tricks are Important for Learning to Rank?

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games

On Investigating the Conservative Property of Score-Based Generative Models

Curriculum Co-disentangled Representation Learning across Multiple Environments for Social Recommendation

Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching

UPSCALE: Unconstrained Channel Pruning

Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference

Fair and Optimal Multi-Class Classification via Post-Processing

Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks

Optimizing Mode Connectivity for Class Incremental Learning

Never mind the metrics---what about the uncertainty? Visualising confusion matrix metric distributions

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Provable Dynamic Fusion for Low-Quality Multimodal Data

CLUSTSEG: Clustering for Universal Segmentation

GFlowNet-EM for Learning Compositional Latent Variable Models

SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation

CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification

FAIRER: Fairness as Decision Rationale Alignment

Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning

Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution

Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere

SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning

Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning

Composer: Creative and Controllable Image Synthesis with Composable Conditions

Evolving Semantic Prototype Improves Generative Zero-Shot Learning

ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts

Retrieval-Augmented Multimodal Language Modeling

A Closer Look at Few-shot Classification Again

Boosting Offline Reinforcement Learning with Action Preference Query

Patch-level Contrastive Learning via Positional Query for Visual Pre-training

Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language

Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

Learning GFlowNets From Partial Episodes For Improved Convergence And Stability

Cones: Concept Neurons in Diffusion Models for Customized Generation

Towards Omni-generalizable Neural Methods for Vehicle Routing Problems

Long-Term Rhythmic Video Soundtracker

XAI Beyond Classification: Interpretable Neural Clustering

Selective Machine Learning of the Average Treatment Effect with an Invalid Instrumental Variable

abess: A Fast Best-Subset Selection Library in Python and R

Exploiting locality in high-dimensional Factorial hidden Markov models

FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation

Are Diffusion Models Vulnerable to Membership Inference Attacks?

Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables

CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms

Project and Forget: Solving Large-Scale Metric Constrained Problems

Constraint Reasoning Embedded Structured Prediction

Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks

Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence

On the Convergence Rates of Policy Gradient Methods

Cluster-Specific Predictions with Multi-Task Gaussian Processes

Data-Derived Weak Universal Consistency

A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback

Non-asymptotic Properties of Individualized Treatment Rules from Sequentially Rule-Adaptive Trials

Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks

Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism

Underspecification Presents Challenges for Credibility in Modern Machine Learning

Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima

Towards Learning to Imitate from a Single Video Demonstration

Faith-Shap: The Faithful Shapley Interaction Index

Knowledge Hypergraph Embedding Meets Relational Algebra

Deep linear networks can benignly overfit when shallow ones do

Flexible Model Aggregation for Quantile Regression

Counterfactual Analysis in Dynamic Latent State Models

Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery

Nested Elimination: A Simple Algorithm for Best-Item Identification From Choice-Based Feedback

Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels

Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers

Learning Temporally AbstractWorld Models without Online Experimentation

Consistency of Multiple Kernel Clustering

Robustness in Multimodal Learning under Train-Test Modality Mismatch

NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion

Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit

Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search

Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective

Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions

Discrete Key-Value Bottleneck

TabDDPM: Modelling Tabular Data with Diffusion Models

GFlowOut: Dropout with Generative Flow Networks

Benign Overfitting in Two-layer ReLU Convolutional Neural Networks

BiBench: Benchmarking and Analyzing Network Binarization

Efficient Personalized Federated Learning via Sparse Model-Adaptation

Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation

Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?

Free-Form Variational Inference for Gaussian Process State-Space Models

Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization

The Benefits of Mixup for Feature Learning

EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression

On the Generalization of Multi-modal Contrastive Learning

Fast Sampling of Diffusion Models via Operator Learning

Superhuman Fairness

Cross-Entropy Loss Functions: Theoretical Analysis and Applications

PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient

Optimizing NOTEARS Objectives via Topological Swaps

dugMatting: Decomposed-Uncertainty-Guided Matting

Is Overfitting Necessary for Implicit Video Representation?

Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs

Statistical Inference and A/B Testing for First-Price Pacing Equilibria

Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels

PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search

Forward-Backward Gaussian Variational Inference via JKO in the Bures-Wasserstein Space

Revisiting Pseudo-Label for Single-Positive Multi-Label Learning

WL meet VC

Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability

An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning

How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control

Tilted Sparse Additive Models

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models

Policy Contrastive Imitation Learning

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity

Auxiliary Modality Learning with Generalized Curriculum Distillation

DevFormer: A Symmetric Transformer for Context-Aware Device Placement

HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

Toward Fair and Robust Estimation of Optimal Treatment Regimes

Distribution Free Prediction Sets for Node Classification

Few-Sample Feature Selection via Feature Manifold Learning

Constrained Phi-Equilibria

End-to-end Differentiable Clustering with Associative Memories

Conformal Prediction for Federated Uncertainty Quantification Under Label Shift

Parameter-Level Soft-Masking for Continual Learning

Adversarial robustness of amortized Bayesian inference

Why Is Public Pretraining Necessary for Private Model Training?

End-to-End Multi-Object Detection with a Regularized Mixture Model

Variance Control for Distributional Reinforcement Learning

Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning

Reachability-Aware Laplacian Representation in Reinforcement Learning

Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds

Model-agnostic Measure of Generalization Difficulty

Quantized Distributed Training of Large Models with Convergence Guarantees

Pareto Regret Analyses in Multi-objective Multi-armed Bandit

Contextual Reliability: When Different Features Matter in Different Contexts

Fast Federated Machine Unlearning with Nonlinear Functional Theory

Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction

Feature Expansion for Graph Neural Networks

Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling

On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm

Improving Expert Predictions with Conformal Prediction

PLay: Parametrically Conditioned Layout Generation using Latent Diffusion

The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

Model-Free Robust Average-Reward Reinforcement Learning

LongCoder: A Long-Range Pre-trained Language Model for Code Completion

Change is Hard: A Closer Look at Subpopulation Shift

Secure Federated Correlation Test and Entropy Estimation

Thompson Sampling with Less Exploration is Fast and Optimal

Efficient Online Reinforcement Learning with Offline Data

Understanding the Complexity Gains of Single-Task RL with a Curriculum

Explainability as statistical inference

"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts

Controlled Text Generation with Natural Language Instructions

Representation-Driven Reinforcement Learning

Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks

MultiRobustBench: Benchmarking Robustness Against Multiple Attacks

Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions

The Acquisition of Physical Knowledge in Generative Neural Networks

Text-To-Concept (and Back) via Cross-Model Alignment

Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits

DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference

Communication-Constrained Bandits under Additive Gaussian Noise

A Deep Conjugate Direction Method for Iteratively Solving Linear Systems

Run-off Election: Improved Provable Defense against Data Poisoning Attacks

A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition

Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption

Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation

BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

Submodular Order Functions and Assortment Optimization

AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners

Q-Flow: Generative Modeling for Differential Equations of Open Quantum Dynamics with Normalizing Flows

Quantum 3D Graph Learning with Applications to Molecule Embedding

Reinforcement Learning with History Dependent Dynamic Contexts

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

Multi-User Reinforcement Learning with Low Rank Rewards

Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics

Cluster Explanation via Polyhedral Descriptions

Measuring the Impact of Programming Language Distribution

Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL

Towards Understanding the Role of Attention in Prompt-tuning

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Random Teachers are Good Teachers

Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control

Fully-Adaptive Composition in Differential Privacy

Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems

Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR

Reconstructive Neuron Pruning for Backdoor Defense

RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation

Sequential Underspecified Instrument Selection for Cause-Effect Estimation

Poisoning Language Models During Instruction Tuning

Domain Adaptation Under Relaxed Label Shift

Learning Deep Time-index Models for Time Series Forecasting

AutoCoreset: An Automatic Practical Coreset Construction Framework

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows

Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data

Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability

Efficient Training of Language Models using Few-Shot Learning

Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation

On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation

Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL

Action Matching: Learning Stochastic Dynamics from Samples

Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference

Discover-Then-Rank Unlabeled Support Vectors in the Dual Space for Multi-Class Active Learning

Decentralized SGD and Average-direction SAM are Asymptotically Equivalent

SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series

Hierarchical Learning in Hyperbolic Space: Revisit and Beyond

Evaluating Unsupervised Denoising Requires Unsupervised Metrics

Margin-based sampling in high dimensions: When being active is less efficient than staying passive

Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks

Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts

Fair and Accurate Decision Making through Group-Aware Learning

CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design

Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think

Bidirectional Learning for Offline Model-based Biological Sequence Design

SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching

Loss Balancing for Fair Supervised Learning

TAN Without a Burn: Scaling Laws of DP-SGD

Controllable Neural Symbolic Regression

Predictable MDP Abstraction for Unsupervised Model-Based RL

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills

Online Nonstochastic Control with Adversarial and Static Constraints

EM-Network: Oracle Guided Self-distillation for Sequence Learning

Quantifying Human Priors over Social and Navigation Networks

One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training

Deep Laplacian-based Options for Temporally-Extended Exploration

Structure Learning of Latent Factors via Clique Search on Correlation Thresholded Graphs

Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and MDPs

Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks

Rethinking Visual Reconstruction: Experience-Based Content Completion Guided by Visual Cues

Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality

Continuously Parameterized Mixture Models

Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction

Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation

Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms

Best Arm Identification in Multi-Agent Multi-Armed Bandits

Neural Stochastic Differential Games for Time-series Analysis

Brauer's Group Equivariant Neural Networks

Label differential privacy and private training data release

Data Efficient Neural Scaling Law via Model Reusing

Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-type Samplers

Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation

Learning Neural PDE Solvers with Parameter-Guided Channel Attention

Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design

Truncating Trajectories in Monte Carlo Reinforcement Learning

On the Forward Invariance of Neural ODEs

Global Optimization with Parametric Function Approximation

From Perception to Programs: Regularize, Overparameterize, and Amortize

Identifying Interpretable Subspaces in Image Representations

Online Learning in Stackelberg Games with an Omniscient Follower

Revisiting Sampling for Combinatorial Optimization

The Value of Out-of-Distribution Data

Bridging the Gap between Neural and Classical Approaches in Abstract Geometric Reasoning with Attention-based Lattice Symmetry Priors

Actor-Critic Alignment for Offline-to-Online Reinforcement Learning

Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits

LSDS++ : Dual Sampling for Accelerated k-means++

Locally Regularized Neural Differential Equations: Some Black Boxes were meant to remain closed!

Masked Trajectory Models for Prediction, Representation, and Control

In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation

ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval

The Monge Gap: A Regularizer to Learn All Transport Maps

Raising the Cost of Malicious AI-Powered Image Editing

Polarity Is All You Need to Learn and Transfer Faster

AbODE: Ab initio antibody design using conjoined ODEs

Learning-augmented private algorithms for multiple quantile release

A modern look at the relationship between sharpness and generalization

Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds

RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution

LIV: Language-Image Representations and Rewards for Robotic Control

Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark

Unveiling the Latent Space Geometry of Push-Forward Generative Models

K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs

Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming

Optimal Convergence Rates for Agnostic Nystrom Kernel Learning

Variational Autoencoding Neural Operators

Efficient Parametric Approximations of Neural Network Function Space Distance

A Unifying Framework to the Analysis of Interaction Methods using Synergy Functions

Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels

Distribution Free Domain Generalization

Theory on Forgetting and Generalization of Continual Learning

Robust Situational Reinforcement Learning in Face of Context Disturbances

Trapdoor Normalization with Irreversible Ownership Verification

Discover and Cure: Concept-aware Mitigation of Spurious Correlation

DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models

Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference

KDEformer: Accelerating Transformers via Kernel Density Estimation

DoCoFL: Downlink Compression for Cross-Device Federated Learning

Learning Representations without Compositional Assumptions

Deterministic equivalent and error universality of deep random features learning

Fast Algorithms for Distributed k-Clustering with Outliers

Minimax estimation of discontinuous optimal transport maps: The semi-discrete case

Robust Budget Pacing with a Single Sample

Compositional Exemplars for In-context Learning

Evaluating Self-Supervised Learning via Risk Decomposition

Looped Transformers as Programmable Computers

Generating Language Corrections for Teaching Physical Control Tasks

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

Does Continual Learning Equally Forget All Parameters?

Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning

Sparsity by Redundancy: Solving $L_1$ with SGD

Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization

Evidential Interactive Learning for Medical Image Captioning

Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy

Sequential Changepoint Detection via Backward Confidence Sequences

Robust Consensus in Ranking Data Analysis: Definitions, Properties and Computational Issues

Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples

simple diffusion: End-to-end diffusion for high resolution images

Multi-class Graph Clustering via Approximated Effective $p$-Resistance

Chemically Transferable Generative Backmapping of Coarse-Grained Proteins

Layered State Discovery for Incremental Autonomous Exploration

CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data

QuantumDARTS: Differentiable Quantum Architecture Search for Variational Quantum Algorithms

Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time

High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance

Phase-aware Adversarial Defense for Improving Adversarial Robustness

LeadFL: Client Self-Defense against Model Poisoning in Federated Learning

Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions

Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification

Language Instructed Reinforcement Learning for Human-AI Coordination

A Neural PDE Solver with Temporal Stencil Modeling

On Second-Order Scoring Rules for Epistemic Uncertainty Quantification

Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classification

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach

Distance Weighted Supervised Learning for Offline Interaction Data

PCA-based Multi-Task Learning: a Random Matrix Approach

Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity

Optimizing Hyperparameters with Conformal Quantile Regression

Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC

Bandits with Knapsacks: Advice on Time-Varying Demands

Adaptive Compositional Continual Meta-Learning

One-Shot Compression of Large Edge-Exchangeable Graphs using Bits-Back Coding

Differentially Private Hierarchical Clustering with Provable Approximation Guarantees

Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees

Equivariant Polynomials for Graph Neural Networks

Learning Intuitive Policies Using Action Features

Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels

Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps

LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework

Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling

Improving Graph Neural Networks with Learnable Propagation Operators

Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum

Effective Neural Topic Modeling with Embedding Clustering Regularization

The Price of Differential Privacy under Continual Observation

Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Linear Speedup and Partial Participation

Equivariance with Learned Canonicalization Functions

Future-conditioned Unsupervised Pretraining for Decision Transformer

Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set

Approximate Thompson Sampling with Logarithmic Batches: Bandits and Reinforcement Learning

Reprogramming Pretrained Language Models for Antibody Sequence Infilling

Supported Trust Region Optimization for Offline Reinforcement Learning

Minimizing Trajectory Curvature of ODE-based Generative Models

Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization

Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space

Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation

Difference-in-Differences Meets Tree-based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding

Generative Adversarial Symmetry Discovery

On Excess Mass Behavior in Gaussian Mixture Models with Orlicz-Wasserstein Distances

Repository-Level Prompt Generation for Large Language Models of Code

Offline Learning in Markov Games with General Function Approximation

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

Fairness in Matching under Uncertainty

Learning Unnormalized Statistical Models via Compositional Optimization

Tensor Gaussian Process with Contraction for Multi-Channel Imaging Analysis

A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints

Scaling Laws for Multilingual Neural Machine Translation

Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network

Likelihood Adjusted Semidefinite Programs for Clustering Heterogeneous Data

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy

Understanding Self-Distillation in the Presence of Label Noise

Data-Driven Subgroup Discovery for Linear Regression

Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions

Smooth Non-stationary Bandits

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

Formalizing Preferences Over Runtime Distributions

Second-order regression models exhibit progressive sharpening to the edge of stability

Scaling Spherical CNNs

Why does Throwing Away Data Improve Worst-Group Error?

Interventional Causal Representation Learning

On the Statistical Benefits of Temporal Difference Learning

Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation

Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing

A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations

Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes

Fairness in Streaming Submodular Maximization over a Matroid Constraint

Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons

Generalized Teacher Forcing for Learning Chaotic Dynamics

Distortion and Uncertainty Aware Loss for Panoramic Depth Completion

Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?

Why Random Pruning Is All We Need to Start Sparse

FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning

On the Robustness of Text Vectorizers

SpotEM: Efficient Video Search for Episodic Memory

Multi-task Hierarchical Adversarial Inverse Reinforcement Learning

Hierarchical Imitation Learning with Vector Quantized Models

Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints

Unscented Autoencoder

Vector-Valued Control Variates

Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation

Expected Gradients of Maxout Networks and Consequences to Parameter Initialization

Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection

Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping

AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation

A Closer Look at Self-Supervised Lightweight Vision Transformers

Uncovering Adversarial Risks of Test-Time Adaptation

Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost

Fast Inference from Transformers via Speculative Decoding

Fair Densities via Boosting the Sufficient Statistics of Exponential Families

Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes

Offline Reinforcement Learning with Closed-Form Policy Improvement Operators

Difference of submodular minimization via DC programming

A Fast Optimistic Method for Monotone Variational Inequalities

Neural Prediction Errors enable Analogical Visual Reasoning in Human Standard Intelligence Tests

Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

Mitigating Memorization of Noisy Labels by Clipping the Model Prediction

A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening

Revisiting Simple Regret: Fast Rates for Returning a Good Arm

Escaping saddle points in zeroth-order optimization: the power of two-point estimators

Beyond the Edge of Stability via Two-step Gradient Updates

Perturbation Analysis of Neural Collapse

PWSHAP: A Path-Wise Explanation Model for Targeted Variables

Tighter Bounds on the Expressivity of Transformer Encoders

Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language

Dual Focal Loss for Calibration

Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval

Disentangled Multiplex Graph Representation Learning

The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent

Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping

Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering

Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning

Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations

Quantum Policy Gradient Algorithm with Optimized Action Decoding

Learning Functional Distributions with Private Labels

Learning Subpocket Prototypes for Generalizable Structure-based Drug Design

Learning Antidote Data to Individual Unfairness

Stratified Adversarial Robustness with Rejection

Marginalization is not Marginal: No Bad VAE Local Minima when Learning Optimal Sparse Representations

Fundamental Tradeoffs in Learning with Prior Information

Does a Neural Network Really Encode Symbolic Concepts?

Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes

Causal Strategic Classification: A Tale of Two Shifts

Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning

MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations

Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization

A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests

Personalized Subgraph Federated Learning

Rethink DARTS Search Space and Renovate a New Benchmark

Optimal LP Rounding and Linear-Time Approximation Algorithms for Clustering Edge-Colored Hypergraphs

Random Shuffle Transformer for Image Restoration

Learning Physical Models that Can Respect Conservation Laws

Leveraging Demonstrations to Improve Online Learning: Quality Matters

Learning-Rate-Free Learning by D-Adaptation

Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs

Efficient exploration via epistemic-risk-seeking policy gradients

GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models

Why Target Networks Stabilise Temporal Difference Methods

Taming graph kernels with random features

SGD-induced drift of representation in a two-layer neural network

Polyhedral Complex Extraction from ReLU Networks using 1-skeleton

Trainability, Expressivity and Interpretability in Gated Neural ODEs

Hidden symmetries of ReLU networks

Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression

Probing the Deep Neural Manifold of Reinforcement Learning to Expose Volatility

Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function

Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization

ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging

Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic Approach

Robust Collaborative Learning with Linear Gradient Overhead

Simple Disentanglement of Style and Content in Visual Representations