AISTATS 2024 Papers

Skip to yearly menu bar Skip to main content

mini compact topic detail

Identifying Confounding from Causal Mechanism Shifts

Riemannian Laplace Approximation with the Fisher Metric

Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures

Minimizing Convex Functionals over Space of Probability Measures via KL Divergence Gradient Flow

Deep Classifier Mimicry without Data Access

Efficient Conformal Prediction under Data Heterogeneity

EM for Mixture of Linear Regression with Clustered Data

BOBA: Byzantine-Robust Federated Learning with Label Skewness

Computing epidemic metrics with edge differential privacy

Optimal Budgeted Rejection Sampling for Generative Models

On the Misspecification of Linear Assumptions in Synthetic Controls

Approximate Leave-one-out Cross Validation for Regression with l1 Regularizers

Simulating weighted automata over sequences and trees with transformers

Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games

Efficient Data Valuation for Weighted Nearest Neighbor Algorithms

Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks

Scalable Higher-Order Tensor Product Spline Models

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective

HintMiner: Automatic Question Hints Mining From Q\&A Web Posts with Language Model via Self-Supervised Learning

DNNLasso: Scalable Graph Learning for Matrix-Variate Data

Robust Non-linear Normalization of Heterogeneous Feature Distributions with Adaptive Tanh-Estimators

Fair k-center Clustering with Outliers

Efficient Quantum Agnostic Improper Learning of Decision Trees

TenGAN: Pure Transformer Encoders Make an Efficient Discrete GAN for De Novo Molecular Generation

Proximal Causal Inference for Synthetic Control with Surrogates

Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers

Is this model reliable for everyone? Testing for strong calibration

Unified Transfer Learning in High-Dimensional Linear Regression

Fair Soft Clustering

Subsampling Error in Stochastic Gradient Langevin Diffusions

Minimax optimal density estimation using a shallow generative model with a one-dimensional latent variable

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability

TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression

Distributionally Robust Quickest Change Detection using Wasserstein Uncertainty Sets

Online Learning in Contextual Second-Price Pay-Per-Click Auctions

Solving Attention Kernel Regression Problem via Pre-conditioner

Causal Discovery under Off-Target Interventions

Multi-Resolution Active Learning of Fourier Neural Operators

Optimal Sparse Survival Trees

Model-based Policy Optimization under Approximate Bayesian Inference

Don't Be Pessimistic Too Early: Look K Steps Ahead!

Positivity-free Policy Learning with Observational Data

Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels

Extragradient Type Methods for Riemannian Variational Inequality Problems

Structural perspective on constraint-based learning of Markov networks

Analysis of Privacy Leakage in Federated Large Language Models

Gaussian process regression with Sliced Wasserstein Weisfeiler-Lehman graph kernels

Lower-level Duality Based Reformulation and Majorization Minimization Algorithm for Hyperparameter Optimization

An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization

Best Arm Identification with Resource Constraints

Dissimilarity Bandits

Identifying Copeland Winners in Dueling Bandits with Indifferences

Robust variance-regularized risk minimization with concomitant scaling

Double InfoGAN for Contrastive Analysis

Efficient Neural Architecture Design via Capturing Architecture-Performance Joint Distribution

Smoothness-Adaptive Dynamic Pricing with Nonparametric Demand Learning

Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models

Online Distribution Learning with Local Privacy Constraints

Personalized Federated X-armed Bandit

FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning

Conformalized Deep Splines for Optimal and Efficient Prediction Sets

A General Algorithm for Solving Rank-one Matrix Sensing

Pure Exploration in Bandits with Linear Constraints

Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting

Data-Driven Online Model Selection With Regret Guarantees

Filter, Rank, and Prune: Learning Linear Cyclic Gaussian Graphical Models

Graph Partitioning with a Move Budget

Feasible $Q$-Learning for Average Reward Reinforcement Learning

Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification

Better Batch for Deep Probabilistic Time Series Forecasting

A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models

Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation

Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes

Directed Hypergraph Representation Learning for Link Prediction

Error bounds for any regression model using Gaussian processes with gradient information

Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers

Autoregressive Bandits

A 4-Approximation Algorithm for Min Max Correlation Clustering

The Risks of Recourse in Binary Classification

From Data Imputation to Data Cleaning --- Automated Cleaning of Tabular Data Improves Downstream Predictive Performance

Provable local learning rule by expert aggregation for a Hawkes network

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation

Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games

Corruption-Robust Offline Two-Player Zero-Sum Markov Games

DHMConv: Directed Hypergraph Momentum Convolution Framework

Achieving Fairness through Separability: A Unified Framework for Fair Representation Learning

Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets

Mixed variational flows for discrete variables

Offline Policy Evaluation and Optimization Under Confounding

Pr{I}sing: Privacy-Preserving Peer Effect Estimation via {I}sing Model

Differentially Private Reward Estimation with Preference Feedback

Adaptivity of Diffusion Models to Manifold Structures

Learning Sampling Policy to Achieve Fewer Queries for Zeroth-Order Optimization

Robust SVD Made Easy: A fast and reliable algorithm for large-scale data analysis

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition

Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean

A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning

Informative Path Planning with Limited Adaptivity

Reparameterized Variational Rejection Sampling

Identification and Estimation of ``Causes of Effects'' using Covariate-Mediator Information

VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates

Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components

A Neural Architecture Predictor based on GNN-Enhanced Transformer

Conformal Contextual Robust Optimization

MMD-based Variable Importance for Distributional Random Forest

Sparse and Faithful Explanations Without Sparse Models

Information-theoretic Analysis of Bayesian Test Data Sensitivity

Theory-guided Message Passing Neural Network for Probabilistic Inference

Robust Offline Reinforcement Learning with Heavy-Tailed Rewards

Recovery Guarantees for Distributed-OMP

Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?

Learning Latent Partial Matchings with Gumbel-IPF Networks

Online non-parametric likelihood-ratio estimation by Pearson-divergence functional minimization

A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent

A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization

Learning-Based Algorithms for Graph Searching Problems

Adaptive Experiment Design with Synthetic Controls

Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks

On cyclical MCMC sampling

Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning

When No-Rejection Learning is Consistent for Regression with Rejection

Towards Achieving Sub-linear Regret and Hard Constraint Violation in Model-free RL

Testing Generated Distributions in GANs to Penalize Mode Collapse

Near-Optimal Convex Simple Bilevel Optimization with a Bisection Method

Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses

Understanding Progressive Training Through the Framework of Randomized Coordinate Descent

Continual Domain Adversarial Adaptation via Double-Head Discriminators

Stochastic Approximation with Biased MCMC for Expectation Maximization

Scalable Algorithms for Individual Preference Stable Clustering

Diagonalisation SGD: Fast \& Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing

Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes

Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias

Non-Convex Joint Community Detection and Group Synchronization via Generalized Power Method

DAGnosis: Localized Identification of Data Inconsistencies using Structures

Looping in the Human: Collaborative and Explainable Bayesian Optimization

Robust Sparse Voting

Intrinsic Gaussian Vector Fields on Manifolds

Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates

Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity

Multi-Domain Causal Representation Learning via Weak Distributional Invariances

Restricted Isometry Property of Rank-One Measurements with Random Unit-Modulus Vectors

GmGM: a fast multi-axis Gaussian graphical model

The Galerkin method beats Graph-Based Approaches for Spectral Algorithms

Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains

Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging

An Online Bootstrap for Time Series

Multi-Dimensional Hyena for Spatial Inductive Bias

On Feynman–Kac training of partial Bayesian neural networks

Fixed-Budget Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit

On the connection between Noise-Contrastive Estimation and Contrastive Divergence

Monitoring machine learning-based risk prediction algorithms in the presence of performativity

A Scalable Algorithm for Individually Fair k-Means Clustering

Equivariant bootstrapping for uncertainty quantification in imaging inverse problems

On Ranking-based Tests of Independence

Comparing Comparators in Generalization Bounds

Ordinal Potential-based Player Rating

Bures-Wasserstein Means of Graphs

Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent

Fast Dynamic Sampling for Determinantal Point Processes

Tackling the XAI Disagreement Problem with Regional Explanations

Scalable Learning of Item Response Theory Models

Causal Modeling with Stationary Diffusions

Revisiting the Noise Model of Stochastic Gradient Descent

Lexicographic Optimization: Algorithms and Stability

Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis

Symmetric Equilibrium Learning of VAEs

Neural McKean Vlasov Processes: Distributional Dependence in Diffusion Models

Variational Gaussian Process Diffusion Processes

Independent Learning in Constrained Markov Potential Games

GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models

Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks

Generalization Bounds for Label Noise Stochastic Gradient Descent

Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters

Clustering Items From Adaptively Collected Inconsistent Feedback

Sequence Length Independent Norm-Based Generalization Bounds for Transformers

Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems

On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions

Acceleration and Implicit Regularization in Gaussian Phase Retrieval

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem

Differentiable Rendering with Reparameterized Volume Sampling

Efficient Low-Dimensional Compression of Overparameterized Models

How Good is a Single Basin?

MINTY: Rule-based models that minimize the need for imputing features with missing values

Multitask Online Learning: Listen to the Neighborhood Buzz

On The Temporal Domain of Differential Equation Inspired Graph Neural Networks

Multi-armed bandits with guaranteed revenue per arm

Bayesian Semi-structured Subspace Inference

Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation

Achieving Group Distributional Robustness and Minimax Group Fairness with Interpolating Classifiers

Nonparametric Automatic Differentiation Variational Inference with Spline Approximation

Functional Flow Matching

Length independent PAC-Bayes bounds for Simple RNNs

Fast 1-Wasserstein distance approximations using greedy strategies

A General Theoretical Paradigm to Understand Learning from Human Preferences

Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization

On the estimation of persistence intensity functions and linear representations of persistence diagrams

Transductive conformal inference with adaptive scores

Differentially Private Conditional Independence Testing

Surrogate Bayesian Networks for Approximating Evolutionary Games

Interpretable Causal Inference for Analyzing Wearable, Sensor, and Distributional Data

Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes

Communication-Efficient Federated Learning With Data and Client Heterogeneity

Identifiable Feature Learning for Spatial Data with Nonlinear ICA

Mixture-of-Linear-Experts for Long-term Time Series Forecasting

Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures

Any-dimensional equivariant neural networks

Learning to Rank for Optimal Treatment Allocation Under Resource Constraints

Importance Matching Lemma for Lossy Compression with Side Information

Optimising Distributions with Natural Gradient Surrogates

Robust Approximate Sampling via Stochastic Gradient Barker Dynamics

Fair Machine Unlearning: Data Removal while Mitigating Disparities

Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach

Backward Filtering Forward Deciding in Linear Non-Gaussian State Space Models

Fitting ARMA Time Series Models without Identification: A Proximal Approach

Constant or Logarithmic Regret in Asynchronous Multiplayer Bandits with Limited Communication

Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions

A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport

NoisyMix: Boosting Model Robustness to Common Corruptions

Fairness in Submodular Maximization over a Matroid Constraint

A Unifying Variational Framework for Gaussian Process Motion Planning

Confident Feature Ranking

Identifiability of Product of Experts Models

An Improved Algorithm for Learning Drifting Discrete Distributions

Soft-constrained Schr\"odinger Bridge: a Stochastic Control Approach

SADI: Similarity-Aware Diffusion Model-Based Imputation for Incomplete Temporal EHR Data

Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors

Resilient Constrained Reinforcement Learning

Adaptive Discretization for Event PredicTion (ADEPT)

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training

Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective

Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity

Contextual Bandits with Budgeted Information Reveal

Enhancing Distributional Stability among Sub-populations

Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems

DE-HNN: An effective neural model for Circuit Netlist representation

Imposing Fairness Constraints in Synthetic Data Generation

Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees

Causal Q-Aggregation for CATE Model Selection

Safe and Interpretable Estimation of Optimal Treatment Regimes

Federated Linear Contextual Bandits with Heterogeneous Clients

The effect of Leaky ReLUs on the training and generalization of overparameterized networks

General Identifiability and Achievability for Causal Representation Learning

Surrogate Active Subspaces for Jump-Discontinuous Functions

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Uncertainty-aware Continuous Implicit Neural Representations for Remote Sensing Object Counting

Sample Efficient Learning of Factored Embeddings of Tensor Fields

Emergent specialization from participation dynamics and multi-learner retraining

Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning

Conformalized Semi-supervised Random Forest for Classification and Abnormality Detection

Trigonometric Quadrature Fourier Features for Scalable Gaussian Process Regression

Causal Bandits with General Causal Models and Interventions

On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective

Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach

Can Probabilistic Feedback Drive User Impacts in Online Platforms?

Stochastic Multi-Armed Bandits with Strongly Reward-Dependent Delays

Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression

Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods

Tensor-view Topological Graph Neural Network

Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate

Contextual Directed Acyclic Graphs

Coreset Markov chain Monte Carlo

Deep Learning-Based Alternative Route Computation

Oracle-Efficient Pessimism: Offline Policy Optimization In Contextual Bandits

Operationalizing Counterfactual Metrics: Incentives, Ranking, and Information Asymmetry

Low-rank MDPs with Continuous Action Spaces

Optimal Exploration is no harder than Thompson Sampling

Towards Practical Non-Adversarial Distribution Matching

Adaptive Quasi-Newton and Anderson Acceleration Framework with Explicit Global (Accelerated) Convergence Rates

Simple and scalable algorithms for cluster-aware precision medicine

Efficient Variational Sequential Information Control

The Effective Number of Shared Dimensions Between Paired Datasets

Adaptive and non-adaptive minimax rates for weighted Laplacian-Eigenmap based nonparametric regression

Learning Policies for Localized Interventions from Observational Data

Score Operator Newton transport

Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts

Directional Optimism for Safe Linear Bandits

Electronic Medical Records Assisted Digital Clinical Trial Design

Near-optimal Per-Action Regret Bounds for Sleeping Bandits

Strategic Usage in a Multi-Learner Setting

On Parameter Estimation in Deviated Gaussian Mixture of Experts

On the Privacy of Selection Mechanisms with Gaussian Noise

Fusing Individualized Treatment Rules Using Secondary Outcomes

Conditions on Preference Relations that Guarantee the Existence of Optimal Policies

Pessimistic Off-Policy Multi-Objective Optimization

Spectrum Extraction and Clipping for Implicitly Linear Layers

Multi-objective Optimization via Wasserstein-Fisher-Rao Gradient Flow

Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs

Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate

Consistency of Dictionary-Based Manifold Learning

Invariant Aggregator for Defending against Federated Backdoor Attacks

Submodular Minimax Optimization: Finding Effective Sets

Estimating treatment effects from single-arm trials via latent-variable modeling

Privacy-Preserving Decentralized Actor-Critic for Cooperative Multi-Agent Reinforcement Learning

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems

Thompson Sampling Itself is Differentially Private

Boundary-Aware Uncertainty for Feature Attribution Explainers

Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities

Bayesian Online Learning for Consensus Prediction

autoMALA: Locally adaptive Metropolis-adjusted Langevin algorithm

Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses

Adaptive Compression in Federated Learning via Side Information

On learning history-based policies for controlling Markov decision processes

Understanding the Generalization Benefits of Late Learning Rate Decay

Private Learning with Public Features

Efficient Graph Laplacian Estimation by Proximal Newton

A Greedy Approximation for k-Determinantal Point Processes

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport

Conditional Adjustment in a Markov Equivalence Class

On the Model-Misspecification in Reinforcement Learning

Quantifying Uncertainty in Natural Language Explanations of Large Language Models

Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention

Fast and Adversarial Robust Kernelized SDU Learning

Online Calibrated and Conformal Prediction Improves Bayesian Optimization

Learning multivariate temporal point processes via the time-change theorem

Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective

Integrating Uncertainty Awareness into Conformalized Quantile Regression

Learning to Solve the Constrained Most Probable Explanation Task in Probabilistic Graphical Models

Local Causal Discovery with Linear non-Gaussian Cyclic Models

Quantifying intrinsic causal contributions via structure preserving interventions

First Passage Percolation with Queried Hints

Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization

Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels

Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits \& Dueling Bandits

Equivalence Testing: The Power of Bounded Adaptivity

Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex

On the Nystr\"om Approximation for Preconditioning in Kernel Machines

Mechanics of Next Token Prediction with Self-Attention

Probabilistic Modeling for Sequences of Sets in Continuous-Time

Provable Policy Gradient Methods for Average-Reward Markov Potential Games

Certified private data release for sparse Lipschitz functions

SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits

Federated Experiment Design under Distributed Differential Privacy

Delegating Data Collection in Decentralized Machine Learning

Deep anytime-valid hypothesis testing

How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability

Approximate Bayesian Class-Conditional Models under Continuous Representation Shift

Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification

On the Vulnerability of Fairness Constrained Learning to Malicious Noise

The Solution Path of SLOPE

Learning Fair Division from Bandit Feedback

Queuing dynamics of asynchronous Federated Learning

Timing as an Action: Learning When to Observe and Act

Approximate Control for Continuous-Time POMDPs

Generative Flow Networks as Entropy-Regularized RL

CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference

Reward-Relevance-Filtered Linear Offline Reinforcement Learning

Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints

Self-Supervised Quantization-Aware Knowledge Distillation

Simulation-Based Stacking

Causally Inspired Regularization Enables Domain General Representations

A/B testing under Interference with Partial Network Information

Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization

Ethics in Action: Training Reinforcement Learning Agents for Moral Decision-making In Text-based Adventure Games

Bandit Pareto Set Identification: the Fixed Budget Setting

Unsupervised Change Point Detection in Multivariate Time Series

Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent

A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning

Unsupervised Novelty Detection in Pretrained Representation Space with Locally Adapted Likelihood Ratio

The Relative Gaussian Mechanism and its Application to Private Gradient Descent

Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection

Maximum entropy GFlowNets with soft Q-learning

FedFisher: Leveraging Fisher Information for One-Shot Federated Learning

Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation

Training Implicit Generative Models via an Invariant Statistical Loss

Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process

A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity

Estimation of partially known Gaussian graphical models with score-based structural priors

Data-Adaptive Probabilistic Likelihood Approximation for Ordinary Differential Equations

End-to-end Feature Selection Approach for Learning Skinny Trees

Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data

Online multiple testing with e-values

BlockBoost: Scalable and Efficient Blocking through Boosting

An Impossibility Theorem for Node Embedding

Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications

Manifold-Aligned Counterfactual Explanations for Neural Networks

Testing exchangeability by pairwise betting

Optimal Zero-Shot Detector for Multi-Armed Attacks

Sharp error bounds for imbalanced classification: how many examples in the minority class?

Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion

Multivariate Time Series Forecasting By Graph Attention Networks With Theoretical Guarantees

Learning Populations of Preferences via Pairwise Comparison Queries

THE SAMPLE COMPLEXITY OF ERM IN EUCLIDEAN STOCHASTIC CONVEX OPTIMIZATION

No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints

Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods

Risk Seeking Bayesian Optimization under Uncertainty for Obtaining Extremum

Posterior Uncertainty Quantification in Neural Networks using Data Augmentation

Why is parameter averaging beneficial in SGD? An objective smoothing perspective

Sequential learning of the Pareto front for multi-objective bandits

Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization

Self-Compatibility: Evaluating Causal Discovery without Ground Truth

Learning Sparse Codes with Entropy-Based ELBOs

Faithful graphical representations of local independence

Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels

Variational Resampling

P-tensors: a General Framework for Higher Order Message Passing in Subgraph Neural Networks

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data

Meta Learning in Bandits within shared affine Subspaces

Breaking isometric ties and introducing priors in Gromov-Wasserstein distances

Probabilistic Integral Circuits

Sum-max Submodular Bandits

Fast Fourier Bayesian Quadrature

Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo

Membership Testing in Markov Equivalence Classes via Independence Queries

Exploration via linearly perturbed loss minimisation

SDEs for Minimax Optimization

Compression with Exact Error Distribution for Federated Learning

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits

User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates

Adaptive importance sampling for heavy-tailed distributions via $\alpha$-divergence minimization

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces

Offline Primal-Dual Reinforcement Learning for Linear MDPs

On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers

Attention-based Multi-instance Mixed Models

BLIS-Net: Classifying and Analyzing Signals on Graphs

Classifier Calibration with ROC-Regularized Isotonic Regression

Large-Scale Gaussian Processes via Alternating Projection

Online Learning of Decision Trees with Thompson Sampling

General Tail Bounds for Non-Smooth Stochastic Mirror Descent

Understanding Inverse Scaling and Emergence in Multitask Representation Learning

Faster Recalibration of an Online Predictor via Approachability

Warped Diffusion for Latent Differentiation Inference

A Unified Framework for Discovering Discrete Symmetries

Learning Adaptive Kernels for Statistical Independence Tests

On the Generalization Ability of Unsupervised Pretraining

Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization

Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Consistent Hierarchical Classification with A Generalized Metric

Learning Safety Constraints from Demonstrations with Unknown Rewards

Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations

Efficiently Computable Safety Bounds for Gaussian Processes in Active Learning

Discriminator Guidance for Autoregressive Diffusion Models

Uncertainty Matters: Stable Conclusions under Unstable Assessment of Fairness Results

Mitigating Underfitting in Learning to Defer with Consistent Losses

Time to Cite: Modeling Citation Networks using the Dynamic Impact Single-Event Embedding Model

From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach

Multi-Level Symbolic Regression: Function Structure Learning for Multi-Level Data

Graph fission and cross-validation

Vector Quantile Regression on Manifolds

Interpretability Guarantees with Merlin-Arthur Classifiers

E(3)-Equivariant Mesh Neural Networks

Optimal Transport for Measures with Noisy Tree Metric

Think Global, Adapt Local: Learning Locally Adaptive K-Nearest Neighbor Kernel Density Estimators

Consistent Optimal Transport with Empirical Conditional Measures

Scalable Meta-Learning with Gaussian Processes

RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model

XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage

Orthogonal Gradient Boosting for Simpler Additive Rule Ensembles

SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification

Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors

ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data

Model-Based Best Arm Identification for Decreasing Bandits

Random Oscillators Network for Time Series Processing

Free-form Flows: Make Any Architecture a Normalizing Flow

Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support

Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm

SDMTR: A Brain-inspired Transformer for Relation Inference

Hidden yet quantifiable: A lower bound for confounding strength using randomized trials

LP-based Construction of DC Decompositions for Efficient Inference of Markov Random Fields

On the Expected Size of Conformal Prediction Sets

Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence

Taming False Positives in Out-of-Distribution Detection with Human Feedback

Parameter-Agnostic Optimization under Relaxed Smoothness

Learning to Defer to a Population: A Meta-Learning Approach

Weight-Sharing Regularization

Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing

On the price of exact truthfulness in incentive-compatible online learning with bandit feedback: a regret lower bound for WSU-UX

Graph Machine Learning through the Lens of Bilevel Optimization

Analysis of Kernel Mirror Prox for Measure Optimization

Multi-Agent Learning in Contextual Games under Unknown Constraints

Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty

Probabilistic Calibration by Design for Neural Network Regression

Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent in High-Dimensional Least Squares

Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases

Learning Cartesian Product Graphs with Laplacian Constraints

Prior-dependent analysis of posterior sampling reinforcement learning with function approximation

Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms

Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles

Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation

Inconsistency of Cross-Validation for Structure Learning in Gaussian Graphical Models

Data Driven Threshold and Potential Initialization for Spiking Neural Networks

Learning the Pareto Set Under Incomplete Preferences: Pure Exploration in Vector Bandits

Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures

Anytime-Constrained Reinforcement Learning

Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers

Benefits of Non-Linear Scale Parameterizations in Black Box Variational Inference through Smoothness Results and Gradient Variance Bounds

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity

Optimal estimation of Gaussian (poly)trees

Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation

Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources

Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements

The AL$\ell_0$CORE Tensor Decomposition for Sparse Count Data

Faster Convergence with MultiWay Preferences

Proxy Methods for Domain Adaptation

DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data

Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach

Making Better Use of Unlabelled Data in Bayesian Active Learning

On Convergence in Wasserstein Distance and f-divergence Minimization Problems

Adaptive Federated Minimax Optimization with Lower Complexities

Tight Verification of Probabilistic Robustness in Bayesian Neural Networks

DiffRed: Dimensionality reduction guided by stable rank

Structured Transforms Across Spaces with Cost-Regularized Optimal Transport

Hodge-Compositional Edge Gaussian Processes

Auditing Fairness under Unobserved Confounding

Sample-efficient neural likelihood-free Bayesian inference of implicit HMMs

Non-vacuous Generalization Bounds for Adversarial Risk in Stochastic Neural Networks

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias

Pathwise Explanation of ReLU Neural Networks

Sharpened Lazy Incremental Quasi-Newton Method

Adaptive Batch Sizes for Active Learning: A Probabilistic Numerics Approach

Analysis of Using Sigmoid Loss for Contrastive Learning

On-Demand Federated Learning for Arbitrary Target Class Distributions

Learning Under Random Distributional Shifts

MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization

Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs

Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions

Online learning in bandits with predicted context

Density Uncertainty Layers for Reliable Uncertainty Estimation

To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models

Joint control variate for faster black-box variational inference

Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games

Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling

Sample Complexity Characterization for Linear Contextual MDPs

An Analytic Solution to Covariance Propagation in Neural Networks

Enhancing In-context Learning via Linear Probe Calibration

Cylindrical Thompson Sampling for High-Dimensional Bayesian Optimization

A Doubly Robust Approach to Sparse Reinforcement Learning

Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation

Agnostic Multi-Robust Learning using ERM

Gibbs-Based Information Criteria and the Over-Parameterized Regime

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations

Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference

Categorical Generative Model Evaluation via Synthetic Distribution Coarsening

Benchmarking Observational Studies with Experimental Data under Right-Censoring

Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection

Asynchronous Randomized Trace Estimation

Multi-resolution Time-Series Transformer for Long-term Forecasting

FairRR: Pre-Processing for Group Fairness through Randomized Response

Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts

Towards a Complete Benchmark on Video Moment Localization