AISTATS 2025 Papers

Skip to yearly menu bar Skip to main content

Layout:

mini compact topic detail

Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo

A Shared Low-Rank Adaptation Approach to Personalized RLHF

Semiparametric conformal prediction

Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations

Minimum Empirical Divergence for Sub-Gaussian Linear Bandits

Deeply supervised Nets

Memory-Efficient Optimization with Factorized Hamiltonian Descent

Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphs

Fast Convergence of Softmax Policy Mirror Ascent

Bayesian Gaussian Process ODEs via Double Normalizing Flows

On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network Posteriors

FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts

Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis

SubSearch: Robust Estimation and Outlier Detection for Stochastic Block Models via Subgraph Search

Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs

posteriordb: Testing, Benchmarking and Developing Bayesian Inference Algorithms

Advancing Fairness in Precision Medicine: A Universal Framework for Optimal Treatment Estimation in Censored Data

Solving Estimating Equations With Copulas

Hyperbolic Prototypical Entailment Cones for Image Classification

Signature Isolation Forest

On the Asymptotic Mean Square Error Optimality of Diffusion Models

Best-Arm Identification in Unimodal Bandits

Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory

Restructuring Tractable Probabilistic Circuits

Corruption Robust Offline Reinforcement Learning with Human Feedback

Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments

Policy Teaching via Data Poisoning in Learning from Human Preferences

Poisoning Bayesian Inference via Data Deletion and Replication

Nonparametric Distributional Regression via Quantile Regression

Information-Theoretic Measures on Lattices for Higher-Order Interactions

Contractivity and linear convergence in bilinear saddle-point problems: An operator-theoretic approach

Synthetic Potential Outcomes and Causal Mixture Identifiability

Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms

Analyzing the Role of Permutation Invariance in Linear Mode Connectivity

Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way

Axiomatic Explainer Globalness via Optimal Transport

Bridging the Theoretical Gap in Randomized Smoothing

Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach

Subspace Recovery in Winsorized PCA: Insights into Accuracy and Robustness

Is Gibbs sampling faster than Hamiltonian Monte Carlo on GLMs?

Synthesis and Analysis of Data as Probability Measures With Entropy-Regularized Optimal Transport

Distance Estimation for High-Dimensional Discrete Distributions

Multi-agent Multi-armed Bandit Regret Complexity and Optimality

Anytime-Valid A/B Testing of Counting Processes

Mixed-Feature Logistic Regression Robust to Distribution Shifts

On Local Posterior Structure in Deep Ensembles

Bayesian Inference in Recurrent Explicit Duration Switching Linear Dynamical Systems

Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation

Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent

Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift

On adaptivity and minimax optimality of two-sided nearest neighbors

High-Dimensional Differential Parameter Inference in Exponential Family using Time Score Matching

Learning to Negotiate via Voluntary Commitment

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback

Variational Adversarial Training Towards Policies with Improved Robustness

Global Ground Metric Learning with Applications to scRNA data

Multi-marginal Schrödinger Bridges with Iterative Reference Refinement

Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes

Batch, match, and patch: low-rank approximations for score-based variational inference

Sampling From Multiscale Densities With Delayed Rejection Generalized Hamiltonian Monte Carlo

Calibrated Computation-Aware Gaussian Processes

Robust Classification by Coupling Data Mollification with Label Smoothing

What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?

Distributional Adversarial Loss

Locally Private Sampling with Public Data

Testing Conditional Independence with Deep Neural Network Based Binary Expansion Testing (DeepBET)

Robust Score Matching

Legitimate ground-truth-free metrics for deep uncertainty classification scoring

Conformal Prediction Under Generalized Covariate Shift with Posterior Drift

Transformers are Provably Optimal In-context Estimators for Wireless Communications

Beyond Size-Based Metrics: Measuring Task-Specific Complexity in Symbolic Regression

Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions

Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees

Max-Rank: Efficient Multiple Testing for Conformal Prediction

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis

Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory

Cross-modality Matching and Prediction of Perturbation Responses with Labeled Gromov-Wasserstein Optimal Transport

Bayesian Circular Regression with von Mises Quasi-Processes

On Subjective Uncertainty Quantification and Calibration in Natural Language Generation

LITE: Efficiently Estimating Gaussian Probability of Maximality

Statistical Guarantees for Unpaired Image-to-Image Cross-Domain Analysis using GANs

Fundamental Limits of Perfect Concept Erasure

The Sample Complexity of Stackelberg Games

On the Relationship Between Robustness and Expressivity of Graph Neural Networks

Almost linear time differentially private release of synthetic graphs

Stein Boltzmann Sampling: A Variational Approach for Global Optimization

Active Feature Acquisition for Personalised Treatment Assignment

Balls-and-Bins Sampling for DP-SGD

Tamed Langevin sampling under weaker conditions

Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion

On the Computational Tractability of the (Many) Shapley Values

Calm Composite Losses: Being Improper Yet Proper Composite

Consistent Amortized Clustering via Generative Flow Networks

Cross Validation for Correlated Data in Classification Models

Deep Clustering via Probabilistic Ratio-Cut Optimization

Differentially Private Continual Release of Histograms and Related Queries

Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging

Partial Information Decomposition for Data Interpretability and Feature Selection

Sketch-and-Project Meets Newton Method: Global O(1/k^2) Convergence with Low-Rank Updates

Distribution-Aware Mean Estimation under User-level Local Differential Privacy

QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits

Cost-Aware Optimal Pairwise Pure Exploration

Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space

Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent

SNAP: Sequential Non-Ancestor Pruning for Targeted Causal Effect Estimation With an Unknown Graph

LMEraser: Large Model Unlearning via Adaptive Prompt Tuning

Superiority of Multi-Head Attention: A Theoretical Study in Shallow Transformers in In-Context Linear Regression

Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span

Clustering Context in Off-Policy Evaluation

Kernel Single Proxy Control for Deterministic Confounding

Data Reconstruction Attacks and Defenses: A Systematic Evaluation

Cost-aware simulation-based inference

Algorithmic Accountability in Small Data: Sample-Size-Induced Bias Within Classification Metrics

Signal Recovery from Random Dot-Product Graphs under Local Differential Privacy

Feasible Learning

Score matching for bridges without learning time-reversals

Sequential Kernelized Stein Discrepancy

ClusterSC: Advancing Synthetic Control with Donor Selection

Estimation of Large Zipfian Distributions with Sort and Snap

DPFL: Decentralized Personalized Federated Learning

Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants

Diffusion Models under Group Transformations

On the Sample Complexity of Next-Token Prediction

Function-Space MCMC for Bayesian Wide Neural Networks

Time-series attribution maps with regularized contrastive learning

ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning

Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation

Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition

SINE: Scalable MPE Inference for Probabilistic Graphical Models using Advanced Neural Embeddings

Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons

High-probability Convergence Bounds for Online Nonlinear Stochastic Gradient Descent under Heavy-tailed Noise

Strategic Conformal Prediction

Changepoint Estimation in Sparse Dynamic Stochastic Block Models under Near-Optimal Signal Strength

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration

Pick-to-Learn and Self-Certified Gaussian Process Approximations

Paths and Ambient Spaces in Neural Loss Landscapes

Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage

Integer Programming Based Methods and Heuristics for Causal Graph Learning

TempTest: Local Normalization Distortion and the Detection of Machine-generated Text

UNHaP: Unmixing Noise from Hawkes Processes

Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization

Prediction-Centric Uncertainty Quantification via MMD

HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search

$\mathcal{I}$-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers

When the Universe is Too Big: Bounding Consideration Probabilities for Plackett-Luce Rankings

Inverse Optimization with Prediction Market: A Characterization of Scoring Rules for Elciting System States

Stochastic Rounding for LLM Training: Theory and Practice

A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning

Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties

Safe exploration in reproducing kernel Hilbert spaces

Causal Representation Learning from General Environments under Nonparametric Mixing

Differentially Private Graph Data Release: Inefficiencies & Unfairness

Ordered $\mathcal{V}$-information Growth: A Fresh Perspective on Shared Information

Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning

Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problems

Counting Graphlets of Size k under Local Differential Privacy

MING: A Functional Approach to Learning Molecular Generative Models

Steinmetz Neural Networks for Complex-Valued Data

Knowledge Graph Completion with Mixed Geometry Tensor Factorization

Variational Schr\"odinger Momentum Diffusion

Deep Generative Quantile Bayes

A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks

Change Point Detection in Hadamard Spaces by Alternating Minimization

The Strong Product Model for Network Inference without Independence Assumptions

An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications

Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context

RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks

Online-to-PAC generalization bounds under graph-mixing dependencies

Rate of Model Collapse in Recursive Training

On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients

Order-Optimal Regret in Distributed Kernel Bandits

Unbiased Quantization of the $L_1$ Ball for Communication-Efficient Distributed Mean Estimation

Information-Theoretic Causal Discovery in Topological Order

On the Inherent Privacy of Zeroth-Order Projected Gradient Descent

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses

Weighted Euclidean Distance Matrices over Mixed Continuous and Categorical Inputs for Gaussian Process Models

Improving Stochastic Cubic Newton with Momentum

Fundamental computational limits of weak learnability in high-dimensional multi-index models

The Polynomial Iteration Complexity for Variance Exploding Diffusion Models: Elucidating SDE and ODE Samplers

Bandit Pareto Set Identification in a Multi-Output Linear Model

Learning the Pareto Front Using Bootstrapped Observation Samples

Federated Communication-Efficient Multi-Objective Optimization

Online Assortment and Price Optimization Under Contextual Choice Models

Recurrent Neural Goodness-of-Fit Test for Time Series

Towards Fair Graph Learning without Demographic Information

Parameter estimation in state space models using particle importance sampling

Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector

Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis

High Dimensional Bayesian Optimization using Lasso Variable Selection

Approximate information maximization for bandit games

Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization

Bridging Domains with Approximately Shared Features

Cross-Modal Imputation and Uncertainty Estimation for Spatial Transcriptomics

Infinite-dimensional Diffusion Bridge Simulation via Operator Learning

Collaborative non-parametric two-sample testing

A Unified Evaluation Framework for Epistemic Predictions

Distributional Counterfactual Explanations With Optimal Transport

Information Transfer Across Clinical Tasks via Adaptive Parameter Optimisation

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

Vecchia Gaussian Process Ensembles on Internal Representations of Deep Neural Networks

Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control

Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices

Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory

Locally Optimal Descent for Dynamic Stepsize Scheduling

Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections

Gaussian Mean Testing under Truncation

Memorization in Attention-only Transformers

Computing high-dimensional optimal transport by flow neural networks

Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization

Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation

Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning

Meta-learning Task-specific Regularization Weights for Few-shot Linear Regression

FLIPHAT: Joint Differential Privacy for High Dimensional Linear Bandits

Asynchronous Decentralized Optimization with Constraints: Achievable Speeds of Convergence for Directed Graphs

Nonparametric Factor Analysis and Beyond

Evidential Uncertainty Probes for Graph Neural Networks

Structure based SAT dataset for analysing GNN generalisation

Optimal Multi-Objective Best Arm Identification with Fixed Confidence

Nyström Kernel Stein Discrepancy

Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model

Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation

AxlePro: Momentum-Accelerated Batched Training of Kernel Machines

Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators

Decoupling epistemic and aleatoric uncertainties with possibility theory

Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting

Density-Dependent Group Testing

Bilevel Reinforcement Learning via the Development of Hyper-gradient without Lower-Level Convexity

Infinite Width Limits of Self Supervised Neural Networks

Learning the Distribution Map in Reverse Causal Performative Prediction

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities

Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings

A Differential Inclusion Approach for Learning Heterogeneous Sparsity in Neuroimaging Analysis

DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification

Theoretical Analysis of Leave-one-out Cross Validation for Non-differentiable Penalties under High-dimensional Settings

ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data

Differentially private algorithms for linear queries via stochastic convex optimization

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs

Zero-Shot Action Generalization with Limited Observations

Conditional Prediction ROC Bands for Graph Classification

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs

M$^2$AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding

Approximate Global Convergence of Independent Learning in Multi-Agent Systems

Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality

Multi-Agent Credit Assignment with Pretrained Language Models

Harnessing Causality in Reinforcement Learning with Bagged Decision Times

Consistent Validation for Predictive Methods in Spatial Settings

Fairness Risks for Group-Conditionally Missing Demographics

Scalable spectral representations for multiagent reinforcement learning in network MDPs

Towards a mathematical theory for consistency training in diffusion models

SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity

From Gradient Clipping to Normalization for Heavy Tailed SGD

Trustworthy assessment of heterogeneous treatment effect estimator via analysis of relative error

Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization

Parabolic Continual Learning

Post-processing for Fair Regression via Explainable SVD

Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration

Graph Machine Learning based Doubly Robust Estimator for Network Causal Effects

Quantifying Knowledge Distillation using Partial Information Decomposition

Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning

A Multi-Task Learning Approach to Linear Multivariate Forecasting

A Computation-Efficient Method of Measuring Dataset Quality based on the Coverage of the Dataset

A kernel Stein test for comparing latent variable models

Scalable Out-of-Distribution Robustness in the Presence of Unobserved Confounders

TRADE: Transfer of Distributions between External Conditions with Normalizing Flows

Copula Based Trainable Calibration Error Estimator of Multi-Label Classification with Label Interdependencies

Analyzing Generative Models by Manifold Entropic Metrics

Model-Based Causal Feature Selection for General Response Types

Common Learning Constraints Alter Interpretations of Direct Preference Optimization

A Subquadratic Time Approximation Algorithm for Individually Fair k-Center

StableMDS: A Novel Gradient Descent-Based Method for Stabilizing and Accelerating Weighted Multidimensional Scaling

Stochastic Gradient Descent for Bézier Simplex Representation of Pareto Set in Multi-Objective Optimization

Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds

Distributional Off-policy Evaluation with Bellman Residual Minimization

Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields

New User Event Prediction Through the Lens of Causal Inference

All models are wrong, some are useful: Model Selection with Limited Labels

Deep Optimal Sensor Placement for Black Box Stochastic Simulations

A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints

Dissecting the Impact of Model Misspecification in Data-Driven Optimization

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces

Mean-Field Microcanonical Gradient Descent

Koopman-Equivariant Gaussian Processes

Robust Kernel Hypothesis Testing under Data Corruption

Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits

Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment

Neural Point Processes for Pixel-wise Regression

On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond

Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data

Learning from biased positive-unlabeled data via threshold calibration

Differentially Private Range Queries with Correlated Input Perturbation

On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark

Fully Dynamic Adversarially Robust Correlation Clustering in Polylogarithmic Update Time

Cubic regularized subspace Newton for non-convex optimization

Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold

Credal Two-Sample Tests of Epistemic Uncertainty

Get rid of your constraints and reparametrize: A study in NNLS and implicit bias

A Safe Bayesian Learning Algorithm for Constrained MDPs with Bounded Constraint Violation

FedBaF: Federated Learning Aggregation Biased by a Foundation Model

Bayesian Principles Improve Prompt Learning In Vision-Language Models

Decomposing Global Feature Effects Based on Feature Interactions

Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis

Model selection for behavioral learning data and applications to contextual bandits

Geometric Collaborative Filtering with Convergence

Q-function Decomposition with Intervention Semantics for Factored Action Spaces

HR-Bandit: Human-AI Collaborated Linear Recourse Bandit

An Iterative Algorithm for Rescaled Hyperbolic Functions Regression

Computation-Aware Kalman Filtering and Smoothing

The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws

Bayesian Decision Theory on Decision Trees: Uncertainty Evaluation and Interpretability

Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment

Improved dependence on coherence in eigenvector and eigenvalue estimation error bounds

Efficient Optimization Algorithms for Linear Adversarial Training

A Generalized Theory of Mixup for Structure-Preserving Synthetic Data

Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks

Optimising Clinical Federated Learning through Mode Connectivity-based Model Aggregation

Graph-based Complexity for Causal Effect by Empirical Plug-in

A Likelihood Based Approach for Watermark Detection

Learning Graph Node Embeddings by Smooth Pair Sampling

Classification of High-dimensional Time Series in Spectral Domain Using Explainable Features with Applications to Neuroimaging Data

Certifiably Quantisation-Robust training and inference of Neural Networks

Training LLMs with MXFP4

A Shapley-value Guided Rationale Editor for Rationale Learning

Weighted Sum of Gaussian Process Latent Variable Models

Task Shift: From Classification to Regression in Overparameterized Linear Models

Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?

All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling

Reliable and Scalable Variable Importance Estimation via Warm-start and Early Stopping

$q\texttt{POTS}$: Efficient Batch Multiobjective Bayesian Optimization via Pareto Optimal Thompson Sampling

LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits

Unconditionally Calibrated Priors for Beta Mixture Density Networks

Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances

Theory of Agreement-on-the-Line in Linear Models and Gaussian Data

Spectral Differential Network Analysis for High-Dimensional Time Series

Optimizing Neural Network Training and Quantization with Rooted Logistic Objectives

Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows

Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks

Adaptive RKHS Fourier Features for Compositional Gaussian Process Models

Credibility-Aware Multimodal Fusion Using Probabilistic Circuits

Leveraging Frozen Batch Normalization for Co-Training in Source-Free Domain Adaptation

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent

Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI

MDP Geometry, Normalization and Reward Balancing Solvers

Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect

Density Ratio-based Proxy Causal Learning Without Density Ratios

Conditioning diffusion models by explicit forward-backward bridging

Permutation Invariant Functions: Statistical Testing, Density Estimation, and Metric Entropy

Understanding the Effect of GCN Convolutions in Regression Tasks

Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts

Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning

Pure Exploration with Feedback Graphs

Powerful batch conformal prediction for classification

An Adaptive Method for Weak Supervision with Drifting Data

Regularity in Canonicalized Models: A Theoretical Perspective

Learning Pareto manifolds in high dimensions: How can regularization help?

Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints

Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence

Sparse Activations as Conformal Predictors

A Causal Framework for Evaluating Deferring Systems

Spectral Representation for Causal Estimation with Hidden Confounders

A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets

Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps

TVineSynth: A Truncated C-Vine Copula Generator of Synthetic Tabular Data to Balance Privacy and Utility

Analysis of Two-Stage Rollout Designs with Clustering for Causal Inference under Network Interference

Optimal Stochastic Trace Estimation in Generative Modeling

Posterior Mean Matching: Generative Modeling through Online Bayesian Inference

Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problem

Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation

Selecting the Number of Communities for Weighted Degree-Corrected Stochastic Block Models

Elastic Representation: Mitigating Spurious Correlations for Group Robustness

Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications

Understanding GNNs and Homophily in Dynamic Node Classification

HACSurv: A Hierarchical Copula-Based Approach for Survival Analysis with Dependent Competing Risks

Learning Laplacian Positional Encodings for Heterophilous Graphs

The Uniformly Rotated Mondrian Kernel

Pareto Set Identification With Posterior Sampling

Personalized Convolutional Dictionary Learning of Physiological Time Series

Optimal estimation of linear non-Gaussian structure equation models

Factor Analysis with Correlated Topic Model for Multi-Modal Data

Evaluating Prediction-based Interventions with Human Decision Makers In Mind

MEDUSA: Medical Data Under Shadow Attacks via Hybrid Model Inversion

General Staircase Mechanisms for Optimal Differential Privacy

Microfoundation inference for strategic prediction

Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners

Automatically Adaptive Conformal Risk Control

Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes

Estimation of copulas via Maximum Mean Discrepancy

Radial Neighbors for Provably Accurate Scalable Approximations of Gaussian Processes

Causal discovery in mixed additive noise models

Near-Optimal Algorithm for Non-Stationary Kernelized Bandits

Entropic Matching for Expectation Propagation of Markov Jump Processes

Loss Gradient Gaussian Width based Generalization and Optimization Guarantees

Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation

Variation Due to Regularization Tractably Recovers Bayesian Deep Learning Uncertainty

ScoreFusion: Fusing Score-based Generative Models via Kullback–Leibler Barycenters

Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs

A Novel Convex Gaussian Min Max Theorem for Repeated Features

Variational Inference in Location-Scale Families: Exact Recovery of the Mean and Correlation Matrix

On Distributional Discrepancy for Experimental Design with General Assignment Probabilities

Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data

The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control

Additive Model Boosting: New Insights and Path(ologie)s

Implicit Diffusion: Efficient optimization through stochastic sampling

Statistical Learning of Distributionally Robust Stochastic Control in Continuous State Spaces

A Robust Kernel Statistical Test of Invariance: Detecting Subtle Asymmetries

Offline Multi-task Transfer RL with Representational Penalization

To Give or Not to Give? The Impacts of Strategically Withheld Recourse

Generalized Criterion for Identifiability of Additive Noise Models Using Majorization

Nonparametric estimation of Hawkes processes with RKHSs

The Local Learning Coefficient: A Singularity-Aware Complexity Measure

Continuous Structure Constraint Integration for Robust Causal Discovery

Is Merging Worth It? Securely Evaluating the Information Gain for Causal Dataset Acquisition

Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits

Tensor Network-Constrained Kernel Machines as Gaussian Processes

Theoretically Grounded Pruning of Large Ground Sets for Constrained, Discrete Optimization

Amortized Probabilistic Conditioning for Optimization, Simulation and Inference

Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models

Causal Discovery-Driven Change Point Detection in Time Series

Truncated Inverse-Lévy Measure Representation of the Beta Process

Locally Private Estimation with Public Features

Local Stochastic Sensitivity Analysis For Dynamical Systems

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

Models That Are Interpretable But Not Transparent

Planning and Learning in Risk-Aware Restless Multi-Arm Bandits

Perfect Recovery for Random Geometric Graph Matching with Shallow Graph Neural Networks

Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks

The cost of local and global fairness in Federated Learning

M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling

Beyond Discretization: Learning the Optimal Solution Path

Steering No-Regret Agents in MFGs under Model Uncertainty

Energy-consistent Neural Operators for Hamiltonian and Dissipative Partial Differential Equations

Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits

Adversarial Training in High-Dimensional Regression: Generated Data and Neural Networks

Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing Risks

Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization

Model Evaluation in the Dark: Robust Classifier Metrics with Missing Labels

Performative Reinforcement Learning with Linear Markov Decision Process

What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization

Near-Polynomially Competitive Active Logistic Regression

Statistical Test for Auto Feature Engineering by Selective Inference

From Deep Additive Kernel Learning to Last-Layer Bayesian Neural Networks via Induced Prior Approximation

Disentangling Interactions and Dependencies in Feature Attributions

Differentiable Causal Structure Learning with Identifiability by NOTIME

Differential Privacy in Distributed Learning: Beyond Uniformly Bounded Stochastic Gradients

Scalable Implicit Graphon Learning

Tighter Confidence Bounds for Sequential Kernel Regression

Proximal Sampler with Adaptive Step Size

Robust Offline Policy Learning with Observational Data from Multiple Sources

Conditional Generative Learning from Invariant Representations in Multi-Source: Robustness and Efficiency

Near-Optimal Sample Complexity in Reward-Free Kernel-based Reinforcement Learning

Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy

Tensor Network Based Feature Learning Model

Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy

A Family of Distributions of Random Subsets for Controlling Positive and Negative Dependence

Type Information-Assisted Self-Supervised Knowledge Graph Denoising

Behavior-Inspired Neural Networks for Relational Inference

Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Models

On the Geometry and Optimization of Polynomial Convolutional Networks

Generalization Lower Bounds for GD and SGD in Smooth Stochastic Convex Optimization

RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation

Robust Fair Clustering with Group Membership Uncertainty Sets

Near-optimal algorithms for private estimation and sequential testing of collision probability

InnerThoughts: Disentangling Representations and Predictions in Large Language Models

Variance-Dependent Regret Bounds for Nonstationary Linear Bandits

Offline RL via Feature-Occupancy Gradient Ascent

No-Regret Bayesian Optimization with Stochastic Observation Failures

Time-varying Gaussian Process Bandits with Unknown Prior

Provable Benefits of Task-Specific Prompts for In-context Learning

Global Optimization of Gaussian Process Acquisition Functions Using a Piecewise-Linear Kernel Approximation

Adaptive Extragradient Methods for Root-finding Problems under Relaxed Assumptions

Privacy in Metalearning and Multitask Learning: Modeling and Separations

Strong Screening Rules for Group-based SLOPE Models

Reinforcement Learning for Adaptive MCMC

Separation-Based Distance Measures for Causal Graphs

Level Set Teleportation: An Optimization Perspective

Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models

The Hardness of Validating Observational Studies with Experimental Data

Choice is what matters after Attention

Functional Stochastic Gradient MCMC for Bayesian Neural Networks

Online Student-$t$ Processes with an Overall-local Scale Structure for Modelling Non-stationary Data

Generalization Bounds for Dependent Data using Online-to-Batch Conversion.

Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion

Stochastic Weight Sharing for Bayesian Neural Networks

Learning-Augmented Algorithms for Online Concave Packing and Convex Covering Problems

Recursive Learning of Asymptotic Variational Objectives

S-CFE: Simple Counterfactual Explanations

Learning to Forget: Bayesian Time Series Forecasting using Recurrent Sparse Spectrum Signature Gaussian Processes

AlleNoise - large-scale text classification benchmark dataset with real-world label noise

Dynamic DBSCAN with Euler Tour Sequences

Flexible Copula-Based Mixed Models in Deep Learning: A Scalable Approach to Arbitrary Marginals

From Learning to Optimize to Learning Optimization Algorithms

Explaining ViTs Using Information Flow

Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem

Towards Cost Sensitive Decision Making

Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations

Rethinking Neural-based Matrix Inversion: Why can't, and Where can

Performative Prediction on Games and Mechanism Design

Learning Visual-Semantic Subspace Representations

HAR-former: Hybrid Transformer with an Adaptive Time-Frequency Representation Matrix for Long-Term Series Forecasting

On the Identifiability of Causal Abstractions

InfoNCE: Identifying the Gap Between Theory and Practice

Robust Estimation in metric spaces: Achieving Exponential Concentration with a Fr\'echet Median

Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable

Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability

Noisy Low-Rank Matrix Completion via Transformed $L_1$ Regularization and its Theoretical Properties

A primer on linear classification with missing data

Approximate Equivariance in Reinforcement Learning

When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?

Do Regularization Methods for Shortcut Mitigation Work As Intended?

Multi-Player Approaches for Dueling Bandits

Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis

A Tight Regret Analysis of Non-Parametric Repeated Contextual Brokerage

Safety in the Face of Adversity: Achieving Zero Constraint Violation in Online Learning with Slowly Changing Constraints

Transfer Neyman-Pearson Algorithm for Outlier Detection

$\beta$-th order Acyclicity Derivatives for DAG Learning

Fair Resource Allocation in Weakly Coupled Markov Decision Processes

Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model

Variational Inference on the Boolean Hypercube with the Quantum Entropy

Effective Bayesian Causal Inference via Structural Marginalisation and Autoregressive Orders

Robust Gradient Descent for Phase Retrieval

MODL: Multilearner Online Deep Learning

Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds

Looped ReLU MLPs May Be All You Need as Practical Programmable Computers

Your copula is a classifier in disguise: classification-based copula density estimation

Covariance Selection over Networks

Domain Adaptation and Entanglement: an Optimal Transport Perspective

BudgetIV: Optimal Partial Identification of Causal Effects with Mostly Invalid Instruments

Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs

Optimal downsampling for Imbalanced Classification with Generalized Linear Models

Improving N-Glycosylation and Biopharmaceutical Production Predictions Using AutoML-Built Residual Hybrid Models

Protein Fitness Landscape: Spectral Graph Theory Perspective

Statistical Inference for Feature Selection after Optimal Transport-based Domain Adaptation

Epistemic Uncertainty and Excess Risk in Variational Inference

Differentially Private Kernelized Contextual Bandits

Independent Learning in Performative Markov Potential Games

Natural Language Counterfactual Explanations for Graphs Using Large Language Models

SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching

Global Group Fairness in Federated Learning via Function Tracking

Large Covariance Matrix Estimation With Nonnegative Correlations

Efficient Estimation of a Gaussian Mean with Local Differential Privacy

On Preference-based Stochastic Linear Contextual Bandits with Knapsacks

How Well Can Transformers Emulate In-Context Newton's Method?

Adaptive Convergence Rates for Log-Concave Maximum Likelihood

On Tractability of Learning Bayesian Networks with Ancestral Constraints

On Tradeoffs in Learning-Augmented Algorithms

Approximating the Total Variation Distance between Gaussians

Transfer Learning for High-dimensional Reduced Rank Time Series Models

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference

ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables

Quantile Additive Trend Filtering

Application of Structured State Space Models to High energy physics with locality sensitive hashing

Linear Submodular Maximization with Bandit Feedback

Fixed-Budget Change Point Identification in Piecewise Constant Bandits

Primal-Dual Spectral Representation for Off-policy Evaluation

On the Power of Multitask Representation Learning with Gradient Descent

A Safe Exploration Approach to Constrained Markov Decision Processes

Theoretical Convergence Guarantees for Variational Autoencoders

Bridging Multiple Worlds: Multi-marginal Optimal Transport for Causal Partial-identification Problem

Randomized Iterative Solver as Iterative Refinement: A Simple Fix Towards Backward Stability

Lower Bounds for Time-Varying Kernelized Bandits

Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

Decision-Point Guided Safe Policy Improvement

Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization

Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits

Representer Theorems for Metric and Preference Learning: Geometric Insights and Algorithms

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning

Visualizing token importance for black-box language models

Sparse Causal Effect Estimation using Two-Sample Summary Statistics in the Presence of Unmeasured Confounding

Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents

Out-of-distribution robustness for multivariate analysis via causal regularisation

Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization

Training Neural Samplers with Reverse Diffusive KL Divergence

Causal Temporal Regime Structure Learning

Ant Colony Sampling with GFlowNets for Combinatorial Optimization

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics

Task-Driven Discrete Representation Learning

Learning signals defined on graphs with optimal transport and Gaussian process regression

Infinite-Horizon Reinforcement Learning with Multinomial Logit Function Approximation

Active Bipartite Ranking with Smooth Posterior Distributions

Empirical Error Estimates for Graph Sparsification

$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization

The VampPrior Mixture Model

Clustered Invariant Risk Minimization

Conditional diffusions for amortized neural posterior estimation

Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits

Causal Discovery on Dependent Binary Data

A graphical global optimization framework for parameter estimation of statistical models with nonconvex regularization functions

DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows

On the Consistent Recovery of Joint Distributions from Conditionals

Noise-Aware Differentially Private Variational Inference

Learning High-dimensional Gaussians from Censored Data