AISTATS 2023 Papers

Skip to yearly menu bar Skip to main content

Browse

mini compact topic detail

Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity

Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms

NODAGS-Flow: Nonlinear Cyclic Causal Structure Learning

The ELBO of Variational Autoencoders Converges to a Sum of Entropies

Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck

Algorithm for Constrained Markov Decision Process with Linear Convergence

Actually Sparse Variational Gaussian Processes

Thresholded linear bandits

Blessing of Class Diversity in Pre-training

A Faster Sampler for Discrete Determinantal Point Processes

Deep Joint Source-Channel Coding with Iterative Source Error Correction

Transport Reversible Jump Proposals

Revisiting Weighted Strategy for Non-stationary Parametric Bandits

Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach

FAIR: Fair Collaborative Active Learning with Individual Rationality for Scientific Discovery

Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data

A Tighter Problem-Dependent Regret Bound for Risk-Sensitive Reinforcement Learning

Implications of sparsity and high triangle density for graph representation learning

Distill n' Explain: explaining graph neural networks using simple surrogates

Mediated Uncoupled Learning and Validation with Bregman Divergences: Loss Family with Maximal Generality

Pointwise sampling uncertainties on the Precision-Recall curve

Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees

Can 5th Generation Local Training Methods Support Client Sampling? Yes!

Entropic Risk Optimization in Discounted MDPs

Two-Sample Tests for Inhomogeneous Random Graphs in $L_r$ norm: Optimality and Asymptotics

Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier

Interactive Learning with Pricing for Optimal and Stable Allocations in Markets

Provable Hierarchy-Based Meta-Reinforcement Learning

Loss-Curvature Matching for Dataset Selection and Condensation

Score-based Quickest Change Detection for Unnormalized Models

Convolutional Persistence as a Remedy to Neural Model Analysis

Preferential Subsampling for Stochastic Gradient Langevin Dynamics

Adaptive Cholesky Gaussian Processes

Neural Discovery of Permutation Subgroups

Stochastic Mirror Descent for Large-Scale Sparse Recovery

Unsupervised representation learning with recognition-parametrised probabilistic models

Active Learning for Single Neuron Models with Lipschitz Non-Linearities

One Arrow, Two Kills: A Unified Framework for Achieving Optimal Regret Guarantees for Sleeping Bandits

Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles

Coordinate Descent for SLOPE

Sample Complexity of Distinguishing Cause from Effect

The Lie-Group Bayesian Learning Rule

Learning from Multiple Sources for Data-to-Text and Text-to-Data

Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy

Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions

Sample Complexity of Kernel-Based Q-Learning

Learning Sparse Graphon Mean Field Games

Convex Bounds on the Softmax Function with Applications to Robustness Verification

Does Label Differential Privacy Prevent Label Inference Attacks?

Origins of Low-Dimensional Adversarial Perturbations

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation

Performative Prediction with Neural Networks

Approximating a RUM from Distributions on $k$-Slates

Tight Regret and Complexity Bounds for Thompson Sampling via Langevin Monte Carlo

Prediction-Oriented Bayesian Active Learning

Online Algorithms with Costly Predictions

Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations

A Bregman Divergence View on the Difference-of-Convex Algorithm

Density Ratio Estimation and Neyman Pearson Classification with Missing Data

Inducing Point Allocation for Sparse Gaussian Processes in High-Throughput Bayesian Optimisation

Overparameterized Random Feature Regression with Nearly Orthogonal Data

Federated Learning under Distributed Concept Drift

Learning with Partial Forgetting in Modern Hopfield Networks

Fitting low-rank models on egocentrically sampled partial networks

\{PF\}$^2$ES: Parallel Feasible Pareto Frontier Entropy Search for Multi-Objective Bayesian Optimization

But Are You Sure? An Uncertainty-Aware Perspective on Explainable AI

Fix-A-Step: Semi-supervised Learning From Uncurated Unlabeled Data

Improved Bound on Generalization Error of Compressed KNN Estimator

Agnostic PAC Learning of k-Juntas Using L2-Polynomial Regression

AUC-based Selective Classification

A New Modeling Framework for Continuous, Sequential Domains

Piecewise Stationary Bandits under Risk Criteria

No-regret Sample-efficient Bayesian Optimization for Finding Nash Equilibria with Unknown Utilities

On Model Selection Consistency of Lasso for High-Dimensional Ising Models

A stopping criterion for Bayesian optimization by the gap of expected minimum simple regrets

ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits

Mode-Seeking Divergences: Theory and Applications to GANs

Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data

Multi-Fidelity Bayesian Optimization with Unreliable Information Sources

Discrete Langevin Samplers via Wasserstein Gradient Flow

Resolving the Approximability of Offline and Online Non-monotone DR-Submodular Maximization over General Convex Sets

Dropout-Resilient Secure Multi-Party Collaborative Learning with Linear Communication Complexity

Who Should Predict? Exact Algorithms For Learning to Defer to Humans

Unified Perspective on Probability Divergence via the Density-Ratio Likelihood: Bridging KL-Divergence and Integral Probability Metrics

Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods

Posterior Tracking Algorithm for Classification Bandits

Coherent Probabilistic Forecasting of Temporal Hierarchies

Meta-learning for Robust Anomaly Detection

Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles

Adapting to Latent Subgroup Shifts via Concepts and Proxies

Hierarchical-Hyperplane Kernels for Actively Learning Gaussian Process Models of Nonstationary Systems

Probabilistic Querying of Continuous-Time Event Sequences

Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits

Nothing but Regrets --- Privacy-Preserving Federated Causal Discovery

Improving Adaptive Conformal Prediction Using Self-Supervised Learning

SMCP3: Sequential Monte Carlo with Probabilistic Program Proposals

Compositional Probabilistic and Causal Inference using Tractable Circuit Models

Efficient SAGE Estimation via Causal Structure Learning

Scalable Unbalanced Sobolev Transport for Measures on a Graph

Simulator-Based Inference with WALDO: Confidence Regions by Leveraging Prediction Algorithms and Posterior Estimators for Inverse Problems

qEUBO: A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization

Improved Generalization Bound and Learning of Sparsity Patterns for Data-Driven Low-Rank Approximation

Kernel Conditional Moment Constraints for Confounding Robust Inference

Regression as Classification: Influence of Task Formulation on Neural Network Features

Nystrom Method for Accurate and Scalable Implicit Differentiation

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning

Exploration in Reward Machines with Low Regret

Multi-Agent congestion cost minimization with linear function approximations

Fast Variational Estimation of Mutual Information for Implicit and Explicit Likelihood Models

Frequentist Uncertainty Quantification in Semi-Structured Neural Networks

Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity

Matching Map Recovery with an Unknown Number of Outliers

Deep Value Function Networks for Large-Scale Multistage Stochastic Programming Problems

Randomized geometric tools for anomaly detection in stock markets

Characterizing Polarization in Social Networks using the Signed Relational Latent Distance Model

Smoothly Giving up: Robustness for Simple Models

Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees

Sampling From a Schrödinger Bridge

Combining Graphical and Algebraic Approaches for Parameter Identification in Latent Variable Structural Equation Models

Sample Efficiency of Data Augmentation Consistency Regularization

Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition

Reconstructing Training Data from Model Gradient, Provably

Improved Representation Learning Through Tensorized Autoencoders

Neural Laplace Control for Continuous-time Delayed Systems

Heavy Sets with Applications to Interpretable Machine Learning Diagnostics

Optimal Sketching Bounds for Sparse Linear Regression

High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent

Noise-Aware Statistical Inference with Differentially Private Synthetic Data

Causal Entropy Optimization

Root Cause Identification for Collective Anomalies in Time Series given an Acyclic Summary Causal Graph with Loops

Autoencoded sparse Bayesian in-IRT factorization, calibration, and amortized inference for the Work Disability Functional Assessment Battery

No time to waste: practical statistical contact tracing with few low-bit messages

Singular Value Representation: A New Graph Perspective On Neural Networks

Learning While Scheduling in Multi-Server Systems With Unknown Statistics: MaxWeight with Discounted UCB

NTS-NOTEARS: Learning Nonparametric DBNs With Prior Knowledge

Learning Treatment Effects from Observational and Experimental Data

Mixed-Effect Thompson Sampling

To Impute or not to Impute? Missing Data in Treatment Effect Estimation

SurvivalGAN: Generating Time-to-Event Data for Survival Analysis

Membership Inference Attacks against Synthetic Data through Overfitting Detection

T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression

Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Data

Stochastic Optimization for Spectral Risk Measures

An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge

Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel

Isotropic Gaussian Processes on Finite Spaces of Graphs

Context-Specific Causal Discovery for Categorical Data Using Staged Trees

Mode-constrained Model-based Reinforcement Learning via Gaussian Processes

Diffusion Generative Models in Infinite Dimensions

Bayesian Optimization over High-Dimensional Combinatorial Spaces via Dictionary-based Embeddings

Sparse Bayesian optimization

Probabilities of Causation: Role of Observational Data

HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent

Bayesian Convolutional Deep Sets with Task-Dependent Stationary Prior

Revisiting Fair-PAC Learning and the Axioms of Cardinal Welfare

Privacy-preserving Sparse Generalized Eigenvalue Problem

Conjugate Gradient Method for Generative Adversarial Networks

A Multi-Task Gaussian Process Model for Inferring Time-Varying Treatment Effects in Panel Data

BaCaDI: Bayesian Causal Discovery with Unknown Interventions

Gaussian Processes on Distributions based on Regularized Optimal Transport

Dueling RL: Reinforcement Learning with Trajectory Preferences

Temporal Graph Neural Networks for Irregular Data

A Sea of Words: An In-Depth Analysis of Anchors for Text Data

Average case analysis of Lasso under ultra sparse conditions

PAC-Bayesian Learning of Optimization Algorithms

Delayed Feedback in Generalised Linear Bandits Revisited

Optimism and Delays in Episodic Reinforcement Learning

Active Exploration via Experiment Design in Markov Chains

The Role of Codeword-to-Class Assignments in Error Correcting Codes: An Empirical Study

A Targeted Accuracy Diagnostic for Variational Approximations

Positional Encoder Graph Neural Networks for Geographic Data

Vector Quantized Time Series Generation with a Bidirectional Prior Model

Feasible Recourse Plan via Diverse Interpolation

Learning Constrained Structured Spaces with Application to Multi-Graph Matching

Optimal Algorithms for Latent Bandits with Cluster Structure

Stochastic Tree Ensembles for Estimating Heterogeneous Effects

Conformal Off-Policy Prediction

Nearly Optimal Latent State Decoding in Block MDPs

The Power of Recursion in Graph Neural Networks for Counting Substructures

USIM Gate: Novel Attention-based UpSampling Interpolation Method for Segmenting Precise Boundaries of Target Objects

MMD-B-Fair: Learning Fair Representations with Statistical Testing

Provably Efficient Model-Free Algorithms for Non-stationary CMDPs

On the Privacy Risks of Algorithmic Recourse

Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture

Boosted Off-Policy Learning

Deep Neural Networks with Efficient Guaranteed Invariances

Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path

Collision Probability Matching Loss for Disentangling Epistemic Uncertainty from Aleatoric Uncertainty

“Plus/minus the learning rate”: Easy and Scalable Statistical Inference with SGD

Adversarial robustness of VAEs through the lens of local geometry

SoundSynp: Sound Source Detection from Raw Waveforms with Multi-Scale Synperiodic Filterbanks

Bayesian Structure Scores for Probabilistic Circuits

Robust Variational Autoencoding with Wasserstein Penalty for Novelty Detection

An Unpooling Layer for Graph Generation

Optimal robustness-consistency tradeoffs for learning-augmented metrical task systems

Precision Recall Cover: A Method For Assessing Generative Models

Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery

Towards Balanced Representation Learning for Credit Policy Evaluation

Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes

Bayesian Variable Selection in a Million Dimensions

Estimating Conditional Average Treatment Effects with Missing Treatment Information

Online Defense Strategies for Reinforcement Learning Against Adaptive Reward Poisoning

An Online and Unified Algorithm for Projection Matrix Vector Multiplication with Application to Empirical Risk Minimization

Coarse-Grained Smoothness for Reinforcement Learning in Metric Spaces

Fast Distributed k-Means with a Small Number of Rounds

Langevin Diffusion Variational Inference

Sparse Spectral Bayesian Permanental.Process with Generalized Kernel

Flexible risk design using bi-directional dispersion

Gradient-Informed Neural Network Statistical Robustness Estimation

Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition

Multilevel Bayesian Quadrature

Barlow Graph Auto-Encoder for Unsupervised Network Embedding

Meta-Learning with Adjoint Methods

Robust Linear Regression for General Feature Distribution

The Lauritzen-Chen Likelihood For Graphical Models

On the Capacity Limits of Privileged ERM

AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization

Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision

Statistical Analysis of Karcher Means for Random Restricted PSD Matrices

A Statistical Analysis of Polyak-Ruppert-Averaged Q-Learning

Vector Optimization with Stochastic Bandit Feedback

Mixed Linear Regression via Approximate Message Passing

A principled framework for the design and analysis of token algorithms

Protecting Global Properties of Datasets with Distribution Privacy Mechanisms

MARS: Masked Automatic Ranks Selection in Tensor Decompositions

A New Causal Decomposition Paradigm towards Health Equity

Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation

Improved Robust Algorithms for Learning with Discriminative Feature Feedback

Scalable marked point processes for exchangeable and non-exchangeable event sequences

Neural Simulated Annealing

Adversarial Random Forests for Density Estimation and Generative Modeling

An Homogeneous Unbalanced Regularized Optimal Transport Model with Applications to Optimal Transport with Boundary

Improved Rate of First Order Algorithms for Entropic Optimal Transport

SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval

Learning to Generalize Provably in Learning to Optimize

Reducing Discretization Error in the Frank-Wolfe Method

Online Learning for Traffic Routing under Unknown Preferences

A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space

Universal Agent Mixtures and the Geometry of Intelligence

Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout

Byzantine-Robust Federated Learning with Optimal Statistical Rates

Variational Inference for Neyman-Scott Processes

An Efficient and Continuous Voronoi Density Estimator

Equivariant Representation Learning via Class-Pose Decomposition

Select and Optimize Learning to Solve Large-Scale Traveling Salesman Problem

Unifying local and global model explanations by functional decomposition of low dimensional structures

Fair learning with Wasserstein barycenters for non-decomposable performance measures

Graph Alignment Kernels using Weisfeiler and Leman Hierarchies

Faster Projection-Free Augmented Lagrangian Methods via Weak Proximal Oracle

Recurrent Neural Networks and Universal Approximation of Bayesian Filters

Transport Elliptical Slice Sampling

Reinforcement Learning for Adaptive Mesh Refinement

Mean Parity Fair Regression in RKHS

Minority Oversampling for Imbalanced Data via Class-Preserving Regularized Auto-Encoders

PAC Learning of Halfspaces with Malicious Noise in Nearly Linear Time

Improved Approximation for Fair Correlation Clustering

Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime

Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate

Bayesian Hierarchical Models for Counterfactual Estimation

No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution

Bayesian Strategy-Proof Facility Location via Robust Estimation

Dimensionality Collapse: Optimal Measurement Selection for Low-Error Infinite-Horizon Forecasting

One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning

Learning Robust Graph Neural Networks with Limited Supervision

Benign overfitting of non-smooth neural networks beyond lazy training

Error Estimation for Random Fourier Features

Computing Abductive Explanations for Boosted Trees

Fast Block Coordinate Descent for Non-Convex Group Regularizations

Classification of Adolescents' Risky Behavior in Instant Messaging Conversations

Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data

Model-Based Uncertainty in Value Functions

Uni6Dv2: Noise Elimination for 6D Pose Estimation

Global Convergence of Over-parameterized Deep Equilibrium Models

Model-X Sequential Testing for Conditional Independence via Testing by Betting

Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification

On Universal Portfolios with Continuous Side Information

Global-Local Regularization Via Distributional Robustness

Fair Representation Learning with Unreliable Labels

A Constant-Factor Approximation Algorithm for Reconciliation $k$-Median

Subset verification and search algorithms for causal DAGs

Online Linearized LASSO

On the Complexity of Representation Learning in Contextual Linear Bandits

Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity

BlitzMask: Real-Time Instance Segmentation Approach for Mobile Devices

Variational Boosted Soft Trees

Identification of Blackwell Optimal Policies for Deterministic MDPs

Average Adjusted Association: Efficient Estimation with High Dimensional Confounders

Adversarial De-confounding in Individualised Treatment Effects Estimation

Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework

EGG-GAE: scalable graph neural networks for tabular data imputation

Nonparametric Gaussian Process Covariances via Multidimensional Convolutions

Breaking a Classical Barrier for Classifying Arbitrary Test Examples in the Quantum Model

Sequential Gradient Descent and Quasi-Newton's Method for Change-Point Analysis

Nonparametric Indirect Active Learning

Is interpolation benign for random forest regression?

A Case of Exponential Convergence Rates for SVM

Symmetric (Optimistic) Natural Policy Gradient for Multi-Agent Learning with Parameter Convergence

Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach

Characterizing Internal Evasion Attacks in Federated Learning

Fast Computation of Branching Process Transition Probabilities via ADMM

Active Membership Inference Attack under Local Differential Privacy in Federated Learning

Ideal Abstractions for Decision-Focused Learning

Conformalized Unconditional Quantile Regression

Provable Safe Reinforcement Learning with Binary Feedback

Continuous-Time Decision Transformer for Healthcare Applications

On the Consistency Rate of Decision Tree Learning Algorithms

Fast Feature Selection with Fairness Constraints

Semantic Strengthening of Neuro-Symbolic Learning

Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback

Semi-Verified PAC Learning from the Crowd

ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks

Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions

Influence Diagnostics under Self-concordance

Compress Then Test: Powerful Kernel Testing in Near-linear Time

On Generalization of Decentralized Learning with Separable Data

Differentially Private Synthetic Control

Learning to Optimize for Stochastic Dominance Constraints

High Probability Bounds for Stochastic Continuous Submodular Maximization

Bounding Evidence and Estimating Log-Likelihood in VAE

Consistent Complementary-Label Learning via Order-Preserving Losses

Scalable Bicriteria Algorithms for Non-Monotone Submodular Cover

How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?

Incentive-aware Contextual Pricing with Non-parametric Market Noise

Indeterminacy in Generative Models: Characterization and Strong Identifiability

A Statistical Learning Take on the Concordance Index for Survival Analysis

Minimax-Bayes Reinforcement Learning

Pricing against a Budget and ROI Constrained Buyer

Factorial SDE for Multi-Output Gaussian Process Regression

On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network

Graph Spectral Embedding using the Geodesic Betweenness Centrality

Spectral Augmentations for Graph Contrastive Learning

Efficient fair PCA for fair representation learning

Nonstochastic Contextual Combinatorial Bandits

Retrospective Uncertainties for Deep Models using Vine Copulas

Generative Oversampling for Imbalanced Data via Majority-Guided VAE

Spread Flows for Manifold Modelling

Data Banzhaf: A Robust Data Valuation Framework for Machine Learning

Incremental Aggregated Riemannian Gradient Method for Distributed PCA

ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images

On the Accelerated Noise-Tolerant Power Method

On the bias of K-fold cross validation with stable learners

Balanced Off-Policy Evaluation for Personalized Pricing

A Tale of Sampling and Estimation in Discounted Reinforcement Learning

Deep Grey-Box Models With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond

Tensor-based Kernel Machines with Structured Inducing Points for Large and High-Dimensional Data

EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model

Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves

Direct Inference of Effect of Treatment (DIET) for a Cookieless World

Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling

Rethinking Initialization of the Sinkhorn Algorithm

Theory and Algorithm for Batch Distribution Drift Problems

Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles

Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty

Clustering High-dimensional Data with Ordered Weighted L1 Regularization

Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games

Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations

Calibration of Probabilistic Classifier Sets

CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision

On double-descent in uncertainty quantification in overparametrized models

On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data

Multi-task Representation Learning with Stochastic Linear Bandits

On the Strategyproofness of the Geometric Median

Explicit Regularization in Overparametrized Models via Noise Injection

Theoretically Grounded Loss Functions and Algorithms for Adversarial Robustness

Bures-Wasserstein Barycenters and Low-Rank Matrix Recovery

Do Bayesian Neural Networks Need To Be Fully Stochastic?

Federated Learning for Data Streams

Particle algorithms for maximum likelihood training of latent variable models

Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning

On The Convergence Of Policy Iteration-Based Reinforcement Learning With Monte Carlo Policy Evaluation

Testing of Horn Samplers

Inducing Neural Collapse in Deep Long-tailed Learning

Large deviations rates for stochastic gradient descent with strongly convex functions

Linear Convergence of Gradient Descent For Overparametrized Finite Width Two-Layer Linear Networks With General Initialization

Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining

The Schrödinger Bridge between Gaussian Measures has a Closed Form

Learning k-qubit Quantum Operators via Pauli Decomposition

Meta-Uncertainty in Bayesian Model Comparison

Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models via Reinforcement Learning

Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets

A Contrastive Approach to Online Change Point Detection

DIET: Conditional independence testing with marginal dependence measures of residual information

Scalable Spectral Clustering with Group Fairness Constraints

Manifold Restricted Interventional Shapley Values

A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces

Clustering above Exponential Families with Tempered Exponential Measures

Optimal and Private Learning from Human Response Data

LOFT: Finding Lottery Tickets through Filter-wise Training

Safe Sequential Testing and Effect Estimation in Stratified Count Data

Energy-Based Models for Functional Data using Path Measure Tilting

The Ordered Matrix Dirichlet for State-Space Models

From Shapley Values to Generalized Additive Models and back

Krylov--Bellman boosting: Super-linear policy evaluation in general state spaces

Data Augmentation for Imbalanced Regression

Riemannian Accelerated Gradient Methods via Extrapolation

Federated Asymptotics: a model to compare federated learning algorithms

Near-Optimal Differentially Private Reinforcement Learning

Minimax Nonparametric Two-Sample Test under Adversarial Losses

A Mini-Block Fisher Method for Deep Neural Networks

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

Rank-Based Causal Discovery for Post-Nonlinear Models

On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks

A Blessing of Dimensionality in Membership Inference through Regularization

Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games

The communication cost of security and privacy in federated frequency estimation

Doubly Fair Dynamic Pricing

Implicit Graphon Neural Representation

Uncertainty-aware Unsupervised Video Hashing

Alternating Projected SGD for Equality-constrained Bilevel Optimization

Principled Approaches for Private Adaptation from a Public Source

Multi-armed Bandit Experimental Design: Online Decision-making and Adaptive Inference

Probabilistic Conformal Prediction Using Conditional Random Samples

Regularization for Shuffled Data Problems via Exponential Family Priors on the Permutation Group

TabLLM: Few-shot Classification of Tabular Data with Large Language Models

Online Learning for Non-monotone DR-Submodular Maximization: From Full Information to Bandit Feedback

Provably Efficient Reinforcement Learning via Surprise Bound

Scalable Bayesian Optimization Using Vecchia Approximations of Gaussian Processes

Surveillance Evasion Through Bayesian Reinforcement Learning

Multiple-policy High-confidence Policy Evaluation

On-Demand Communication for Asynchronous Multi-Agent Bandits

Learning Physics-Informed Neural Networks without Stacked Back-propagation

Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAE

TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation

Distributed Offline Policy Optimization Over Batch Data

A Variance-Reduced and Stabilized Proximal Stochastic Gradient Method with Support Identification Guarantees for Structured Optimization

Structure of Nonlinear Node Embeddings in Stochastic Block Models

Robust and Agnostic Learning of Conditional Distributional Treatment Effects

A Finite Sample Complexity Bound for Distributionally Robust Q-learning

Exact Gradient Computation for Spiking Neural Networks via Forward Propagation

Discovering Many Diverse Solutions with Bayesian Optimization

Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation

Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach

Beyond Performative Prediction: Open-environment Learning with Presence of Corruptions

Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection

Adaptive Tuning for Metropolis Adjusted Langevin Trajectories

On the Limitations of the Elo, Real-World Games are Transitive, not Additive

Domain Adaptation under Missingness Shift

ForestPrune: Compact Depth-Pruned Tree Ensembles

Bayesian Optimization with Conformal Prediction Sets

Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games

Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments

Byzantine-Robust Online and Offline Distributed Reinforcement Learning

Second Order Path Variationals in Non-Stationary Online Learning

Approximate Regions of Attraction in Learning with Decision-Dependent Distributions

Active Cost-aware Labeling of Streaming Data

Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints

Competing against Adaptive Strategies in Online Learning via Hints

Wasserstein Distributional Learning via Majorization-Minimization

Wasserstein Distributionally Robust Linear-Quadratic Estimation under Martingale Constraints

Uniformly Conservative Exploration in Reinforcement Learning

Distance-to-Set Priors and Constrained Bayesian Inference

Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables

Distributionally Robust Policy Gradient for Offline Contextual Bandits

Deep equilibrium models as estimators for continuous latent variables

Faithful Heteroscedastic Regression with Neural Networks

Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise

A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem

Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes

Estimating Total Correlation with Mutual Information Estimators

Adversarial Noises Are Linearly Separable for （Nearly） Random Neural Networks

Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion

Cooperative Inverse Decision Theory for Uncertain Preferences

A Unified Perspective on Regularization and Perturbation in Differentiable Subset Selection

Risk Bounds on Aleatoric Uncertainty Recovery

Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation

Adaptation to Misspecified Kernel Regularity in Kernelised Bandits

Randomized Primal-Dual Methods with Adaptive Step Sizes

Overcoming Prior Misspecification in Online Learning to Rank

Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles

Precision/Recall on Imbalanced Test Data

Huber-robust confidence sequences

Learning in RKHM: a C*-algebraic twist for kernel machines

Private Non-Convex Federated Learning Without a Trusted Server

Nonstationary Bandit Learning via Predictive Sampling

Geometric Random Walk Graph Neural Networks via Implicit Layers

Risk-aware linear bandits with convex loss

Strong Lottery Ticket Hypothesis with $\varepsilon$--perturbation

Representation Learning in Deep RL via Discrete Information Bottleneck

Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding

Differentially Private Matrix Completion through Low-rank Matrix Factorization

Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition

Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference

Efficient Informed Proposals for Discrete Distributions via Newton’s Series Approximation

Iterative Teaching by Data Hallucination

Mixtures of All Trees

Probing Graph Representations

Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits

Discrete Distribution Estimation under User-level Local Differential Privacy

Differentiable Change-point Detection With Temporal Point Processes

INO: Invariant Neural Operators for Learning Complex Physical Systems with Momentum Conservation

Using Sliced Mutual Information to Study Memorization and Generalization in Deep Neural Networks

Hedging against Complexity: Distributionally Robust Optimization with Parametric Approximation

Knowledge Acquisition for Human-In-The-Loop Image Captioning

Oblivious near-optimal sampling for multidimensional signals with Fourier constraints

Reinforcement Learning with Stepwise Fairness Constraints