AISTATS 2025 Papers

Layout:

mini compact topic detail

Paths and Ambient Spaces in Neural Loss Landscapes

Automatically Adaptive Conformal Risk Control

Generalized Criterion for Identifiability of Additive Noise Models Using Majorization

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

Locally Private Estimation with Public Features

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

Lower Bounds for Time-Varying Kernelized Bandits

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

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

Efficient Estimation of a Gaussian Mean with Local Differential Privacy

Bayesian Inference in Recurrent Explicit Duration Switching Linear Dynamical Systems

ClusterSC: Advancing Synthetic Control with Donor Selection

Credal Two-Sample Tests of Epistemic Uncertainty

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces

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

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

Optimising Clinical Federated Learning through Mode Connectivity-based Model Aggregation

S-CFE: Simple Counterfactual Explanations

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

Estimation of Large Zipfian Distributions with Sort and Snap

Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks

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

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

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

Bayesian Gaussian Process ODEs via Double Normalizing Flows

The Local Learning Coefficient: A Singularity-Aware Complexity Measure

Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds

Choice is what matters after Attention

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

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

A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets

Approximate information maximization for bandit games

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

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

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

Strong Screening Rules for Group-based SLOPE Models

On the Asymptotic Mean Square Error Optimality of Diffusion Models

Infinite-Horizon Reinforcement Learning with Multinomial Logit Function Approximation

Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation

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

Nyström Kernel Stein Discrepancy

No-Regret Bayesian Optimization with Stochastic Observation Failures

Nonparametric Factor Analysis and Beyond

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

Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Models

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

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

Ant Colony Sampling with GFlowNets for Combinatorial Optimization

Function-Space MCMC for Bayesian Wide Neural Networks

A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning

Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings

Adaptive Extragradient Methods for Root-finding Problems under Relaxed Assumptions

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

Signature Isolation Forest

Elastic Representation: Mitigating Spurious Correlations for Group Robustness

Scalable spectral representations for multiagent reinforcement learning in network MDPs

Bridging Domains with Approximately Shared Features

Epistemic Uncertainty and Excess Risk in Variational Inference

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

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

Empirical Error Estimates for Graph Sparsification

On the Geometry and Optimization of Polynomial Convolutional Networks

Data Reconstruction Attacks and Defenses: A Systematic Evaluation

Locally Private Sampling with Public Data

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

Reinforcement Learning for Adaptive MCMC

Prediction-Centric Uncertainty Quantification via MMD

Harnessing Causality in Reinforcement Learning with Bagged Decision Times

Learning the Pareto Front Using Bootstrapped Observation Samples

FedBaF: Federated Learning Aggregation Biased by a Foundation Model

A Generalized Theory of Mixup for Structure-Preserving Synthetic Data

On the Sample Complexity of Next-Token Prediction

Amortized Probabilistic Conditioning for Optimization, Simulation and Inference

Steering No-Regret Agents in MFGs under Model Uncertainty

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

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

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

Optimal estimation of linear non-Gaussian structure equation models

Stein Boltzmann Sampling: A Variational Approach for Global Optimization

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

Score matching for bridges without learning time-reversals

Safe exploration in reproducing kernel Hilbert spaces

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

On Tradeoffs in Learning-Augmented Algorithms

Consistent Validation for Predictive Methods in Spatial Settings

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

Collaborative non-parametric two-sample testing

Tamed Langevin sampling under weaker conditions

Global Group Fairness in Federated Learning via Function Tracking

Microfoundation inference for strategic prediction

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

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

Fundamental Limits of Perfect Concept Erasure

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

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

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

Distance Estimation for High-Dimensional Discrete Distributions

Type Information-Assisted Self-Supervised Knowledge Graph Denoising

Learning the Distribution Map in Reverse Causal Performative Prediction

Optimizing Neural Network Training and Quantization with Rooted Logistic Objectives

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

Pareto Set Identification With Posterior Sampling

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

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

Q-function Decomposition with Intervention Semantics for Factored Action Spaces

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

Bayesian Decision Theory on Decision Trees: Uncertainty Evaluation and Interpretability

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

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

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

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

Locally Optimal Descent for Dynamic Stepsize Scheduling

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

Policy Teaching via Data Poisoning in Learning from Human Preferences

Model selection for behavioral learning data and applications to contextual bandits

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

Variational Inference on the Boolean Hypercube with the Quantum Entropy

Optimal Multi-Objective Best Arm Identification with Fixed Confidence

Evaluating Prediction-based Interventions with Human Decision Makers In Mind

Bandit Pareto Set Identification in a Multi-Output Linear Model

Efficient Optimization Algorithms for Linear Adversarial Training

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

A primer on linear classification with missing data

Robust Score Matching

On the Relationship Between Robustness and Expressivity of Graph Neural Networks

Parameter estimation in state space models using particle importance sampling

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

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

MING: A Functional Approach to Learning Molecular Generative Models

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

Optimal downsampling for Imbalanced Classification with Generalized Linear Models

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

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

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

UNHaP: Unmixing Noise from Hawkes Processes

Axiomatic Explainer Globalness via Optimal Transport

Integer Programming Based Methods and Heuristics for Causal Graph Learning

The VampPrior Mixture Model

MEDUSA: Medical Data Under Shadow Attacks via Hybrid Model Inversion

Proximal Sampler with Adaptive Step Size

Rate of Model Collapse in Recursive Training

A Shared Low-Rank Adaptation Approach to Personalized RLHF

Differentially private algorithms for linear queries via stochastic convex optimization

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

Recursive Learning of Asymptotic Variational Objectives

Improving Stochastic Cubic Newton with Momentum

Adaptive Convergence Rates for Log-Concave Maximum Likelihood

Learning to Negotiate via Voluntary Commitment

Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization

Fully Dynamic Adversarially Robust Correlation Clustering in Polylogarithmic Update Time

Dynamic DBSCAN with Euler Tour Sequences

Differentially Private Range Queries with Correlated Input Perturbation

An Adaptive Method for Weak Supervision with Drifting Data

On the Inherent Privacy of Zeroth-Order Projected Gradient Descent

Transformers are Provably Optimal In-context Estimators for Wireless Communications

Multi-Player Approaches for Dueling Bandits

Improved dependence on coherence in eigenvector and eigenvalue estimation error bounds

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

Neural Point Processes for Pixel-wise Regression

Minimum Empirical Divergence for Sub-Gaussian Linear Bandits

Dissecting the Impact of Model Misspecification in Data-Driven Optimization

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

Clustered Invariant Risk Minimization

Towards a mathematical theory for consistency training in diffusion models

Training LLMs with MXFP4

Multi-agent Multi-armed Bandit Regret Complexity and Optimality

Models That Are Interpretable But Not Transparent

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

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

AxlePro: Momentum-Accelerated Batched Training of Kernel Machines

A Likelihood Based Approach for Watermark Detection

Bayesian Circular Regression with von Mises Quasi-Processes

Cross Validation for Correlated Data in Classification Models

Post-processing for Fair Regression via Explainable SVD

Truncated Inverse-Lévy Measure Representation of the Beta Process

Consistent Amortized Clustering via Generative Flow Networks

Adaptive RKHS Fourier Features for Compositional Gaussian Process Models

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

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference

On Tractability of Learning Bayesian Networks with Ancestral Constraints

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

Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation

From Learning to Optimize to Learning Optimization Algorithms

Factor Analysis with Correlated Topic Model for Multi-Modal Data

The Hardness of Validating Observational Studies with Experimental Data

Personalized Convolutional Dictionary Learning of Physiological Time Series

Approximating the Total Variation Distance between Gaussians

Performative Prediction on Games and Mechanism Design

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

Partial Information Decomposition for Data Interpretability and Feature Selection

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

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

Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation

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

RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation

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

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

Multi-Agent Credit Assignment with Pretrained Language Models

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

Change Point Detection in Hadamard Spaces by Alternating Minimization

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

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

Differentially Private Continual Release of Histograms and Related Queries

Active Bipartite Ranking with Smooth Posterior Distributions

Information-Theoretic Causal Discovery in Topological Order

A Unified Evaluation Framework for Epistemic Predictions

LMEraser: Large Model Unlearning via Adaptive Prompt Tuning

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

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

Computation-Aware Kalman Filtering and Smoothing

Robust Gradient Descent for Phase Retrieval

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

Calibrated Computation-Aware Gaussian Processes

Towards Fair Graph Learning without Demographic Information

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

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

Disentangling Interactions and Dependencies in Feature Attributions

A Causal Framework for Evaluating Deferring Systems

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

Tensor Network-Constrained Kernel Machines as Gaussian Processes

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

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

Information-Theoretic Measures on Lattices for Higher-Order Interactions

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

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

Common Learning Constraints Alter Interpretations of Direct Preference Optimization

Best-Arm Identification in Unimodal Bandits

ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables

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

Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging

Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning

Distributional Adversarial Loss

A Subquadratic Time Approximation Algorithm for Individually Fair k-Center

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

Credibility-Aware Multimodal Fusion Using Probabilistic Circuits

Near-Polynomially Competitive Active Logistic Regression

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

Fair Resource Allocation in Weakly Coupled Markov Decision Processes

Robust Fair Clustering with Group Membership Uncertainty Sets

FLIPHAT: Joint Differential Privacy for High Dimensional Linear Bandits

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

Conditional diffusions for amortized neural posterior estimation

On adaptivity and minimax optimality of two-sided nearest neighbors

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

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

From Gradient Clipping to Normalization for Heavy Tailed SGD

Deep Optimal Sensor Placement for Black Box Stochastic Simulations

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

Explaining ViTs Using Information Flow

Zero-Shot Action Generalization with Limited Observations

Conditional Prediction ROC Bands for Graph Classification

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

MDP Geometry, Normalization and Reward Balancing Solvers

A Safe Exploration Approach to Constrained Markov Decision Processes

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

Variance-Dependent Regret Bounds for Nonstationary Linear Bandits

Spectral Differential Network Analysis for High-Dimensional Time Series

Time-series attribution maps with regularized contrastive learning

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

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis

An Iterative Algorithm for Rescaled Hyperbolic Functions Regression

Analyzing the Role of Permutation Invariance in Linear Mode Connectivity

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

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

Sampling From Multiscale Densities With Delayed Rejection Generalized Hamiltonian Monte Carlo

Differentially Private Graph Data Release: Inefficiencies & Unfairness

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

Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition

Parabolic Continual Learning

A Multi-Task Learning Approach to Linear Multivariate Forecasting

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

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

Sparse Activations as Conformal Predictors

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

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

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

Spectral Representation for Causal Estimation with Hidden Confounders

Geometric Collaborative Filtering with Convergence

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

Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields

Learning Laplacian Positional Encodings for Heterophilous Graphs

Understanding GNNs and Homophily in Dynamic Node Classification

Causal Discovery on Dependent Binary Data

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

Calm Composite Losses: Being Improper Yet Proper Composite

Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints

Approximate Global Convergence of Independent Learning in Multi-Agent Systems

Protein Fitness Landscape: Spectral Graph Theory Perspective

A Tight Regret Analysis of Non-Parametric Repeated Contextual Brokerage

Evidential Uncertainty Probes for Graph Neural Networks

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

Memory-Efficient Optimization with Factorized Hamiltonian Descent

Computing high-dimensional optimal transport by flow neural networks

Is Gibbs sampling faster than Hamiltonian Monte Carlo on GLMs?

On Preference-based Stochastic Linear Contextual Bandits with Knapsacks

Decoupling epistemic and aleatoric uncertainties with possibility theory

Transfer Learning for High-dimensional Reduced Rank Time Series Models

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

Recurrent Neural Goodness-of-Fit Test for Time Series

Decision-Point Guided Safe Policy Improvement

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

New User Event Prediction Through the Lens of Causal Inference

Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space

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

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

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

Functional Stochastic Gradient MCMC for Bayesian Neural Networks

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

HR-Bandit: Human-AI Collaborated Linear Recourse Bandit

ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning

Domain Adaptation and Entanglement: an Optimal Transport Perspective

Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problems

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

Subspace Recovery in Winsorized PCA: Insights into Accuracy and Robustness

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

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

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

High Dimensional Bayesian Optimization using Lasso Variable Selection

Differentiable Causal Structure Learning with Identifiability by NOTIME

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

Memorization in Attention-only Transformers

Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion

Koopman-Equivariant Gaussian Processes

Continuous Structure Constraint Integration for Robust Causal Discovery

Infinite Width Limits of Self Supervised Neural Networks

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

TRADE: Transfer of Distributions between External Conditions with Normalizing Flows

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

Statistical Test for Auto Feature Engineering by Selective Inference

Offline RL via Feature-Occupancy Gradient Ascent

Differential Privacy in Distributed Learning: Beyond Uniformly Bounded Stochastic Gradients

Performative Reinforcement Learning with Linear Markov Decision Process

On the Identifiability of Causal Abstractions

Powerful batch conformal prediction for classification

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

Fixed-Budget Change Point Identification in Piecewise Constant Bandits

Tensor Network Based Feature Learning Model

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses

Global Ground Metric Learning with Applications to scRNA data

Independent Learning in Performative Markov Potential Games

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

A Differential Inclusion Approach for Learning Heterogeneous Sparsity in Neuroimaging Analysis

Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization

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

Do Regularization Methods for Shortcut Mitigation Work As Intended?

Hyperbolic Prototypical Entailment Cones for Image Classification

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

Covariance Selection over Networks

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

Vecchia Gaussian Process Ensembles on Internal Representations of Deep Neural Networks

Separation-Based Distance Measures for Causal Graphs

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

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

Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization

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

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

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

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

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

Large Covariance Matrix Estimation With Nonnegative Correlations

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

Fairness Risks for Group-Conditionally Missing Demographics

Anytime-Valid A/B Testing of Counting Processes

Diffusion Models under Group Transformations

Theoretical Convergence Guarantees for Variational Autoencoders

Infinite-dimensional Diffusion Bridge Simulation via Operator Learning

Natural Language Counterfactual Explanations for Graphs Using Large Language Models

Nonparametric estimation of Hawkes processes with RKHSs

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

Towards Cost Sensitive Decision Making

Weighted Sum of Gaussian Process Latent Variable Models

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

Density-Dependent Group Testing

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback

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

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

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

On the Computational Tractability of the (Many) Shapley Values

Causal Representation Learning from General Environments under Nonparametric Mixing

Conditioning diffusion models by explicit forward-backward bridging

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

Learning Visual-Semantic Subspace Representations

Kernel Single Proxy Control for Deterministic Confounding

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

Visualizing token importance for black-box language models

Causal Discovery-Driven Change Point Detection in Time Series

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

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

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

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

On Subjective Uncertainty Quantification and Calibration in Natural Language Generation

Primal-Dual Spectral Representation for Off-policy Evaluation

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

Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees

Effective Bayesian Causal Inference via Structural Marginalisation and Autoregressive Orders

Tighter Confidence Bounds for Sequential Kernel Regression

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

InnerThoughts: Disentangling Representations and Predictions in Large Language Models

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

Semiparametric conformal prediction

Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks

Max-Rank: Efficient Multiple Testing for Conformal Prediction

Steinmetz Neural Networks for Complex-Valued Data

Feasible Learning

Task Shift: From Classification to Regression in Overparameterized Linear Models

Fast Convergence of Softmax Policy Mirror Ascent

Scalable Implicit Graphon Learning

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

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

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

DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows

Bridging the Theoretical Gap in Randomized Smoothing

Distributional Off-policy Evaluation with Bellman Residual Minimization

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

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

Linear Submodular Maximization with Bandit Feedback

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

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

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

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

Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy

Bayesian Principles Improve Prompt Learning In Vision-Language Models

Privacy in Metalearning and Multitask Learning: Modeling and Separations

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

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

Learning High-dimensional Gaussians from Censored Data

Deep Generative Quantile Bayes

Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments

InfoNCE: Identifying the Gap Between Theory and Practice

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

Approximate Equivariance in Reinforcement Learning

The cost of local and global fairness in Federated Learning

Local Stochastic Sensitivity Analysis For Dynamical Systems

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

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

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

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

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

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

Synthetic Potential Outcomes and Causal Mixture Identifiability

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

Time-varying Gaussian Process Bandits with Unknown Prior

Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect

Behavior-Inspired Neural Networks for Relational Inference

MODL: Multilearner Online Deep Learning

Active Feature Acquisition for Personalised Treatment Assignment

On the Power of Multitask Representation Learning with Gradient Descent

Graph Machine Learning based Doubly Robust Estimator for Network Causal Effects

Cross-Modal Imputation and Uncertainty Estimation for Spatial Transcriptomics

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

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

Stochastic Rounding for LLM Training: Theory and Practice

Posterior Mean Matching: Generative Modeling through Online Bayesian Inference

Offline Multi-task Transfer RL with Representational Penalization

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

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

Online Assortment and Price Optimization Under Contextual Choice Models

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

Quantifying Knowledge Distillation using Partial Information Decomposition

Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

Cost-Aware Optimal Pairwise Pure Exploration

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

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

Stochastic Weight Sharing for Bayesian Neural Networks

Beyond Discretization: Learning the Optimal Solution Path

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

Causal Temporal Regime Structure Learning

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

General Staircase Mechanisms for Optimal Differential Privacy

Understanding the Effect of GCN Convolutions in Regression Tasks

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints

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

Optimal Stochastic Trace Estimation in Generative Modeling

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

Differentially Private Kernelized Contextual Bandits

Federated Communication-Efficient Multi-Objective Optimization

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

Variational Schr\"odinger Momentum Diffusion

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

The Uniformly Rotated Mondrian Kernel

Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting

Variational Adversarial Training Towards Policies with Improved Robustness

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

Mixed-Feature Logistic Regression Robust to Distribution Shifts

Order-Optimal Regret in Distributed Kernel Bandits

On the Consistent Recovery of Joint Distributions from Conditionals

Transfer Neyman-Pearson Algorithm for Outlier Detection

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

Quantile Additive Trend Filtering

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

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

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

A Shapley-value Guided Rationale Editor for Rationale Learning

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

Regularity in Canonicalized Models: A Theoretical Perspective

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

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

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

Structure based SAT dataset for analysing GNN generalisation

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

Nonparametric Distributional Regression via Quantile Regression

Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators

Deep Clustering via Probabilistic Ratio-Cut Optimization

Gaussian Mean Testing under Truncation

Conformal Prediction Under Generalized Covariate Shift with Posterior Drift

Robust Offline Policy Learning with Observational Data from Multiple Sources

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

Knowledge Graph Completion with Mixed Geometry Tensor Factorization

Unconditionally Calibrated Priors for Beta Mixture Density Networks

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

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

Robust Classification by Coupling Data Mollification with Label Smoothing

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

Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context

LITE: Efficiently Estimating Gaussian Probability of Maximality

Noise-Aware Differentially Private Variational Inference

Counting Graphlets of Size k under Local Differential Privacy

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

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

On Local Posterior Structure in Deep Ensembles

Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning

Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory

Level Set Teleportation: An Optimization Perspective

On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients

Density Ratio-based Proxy Causal Learning Without Density Ratios

Analyzing Generative Models by Manifold Entropic Metrics

DPFL: Decentralized Personalized Federated Learning

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

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

Strategic Conformal Prediction

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

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

Task-Driven Discrete Representation Learning

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

Training Neural Samplers with Reverse Diffusive KL Divergence

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

Mean-Field Microcanonical Gradient Descent

Clustering Context in Off-Policy Evaluation

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

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

The Strong Product Model for Network Inference without Independence Assumptions

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

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

Poisoning Bayesian Inference via Data Deletion and Replication