AISTATS 2026 Papers

Skip to yearly menu bar Skip to main content

Layout:

mini compact topic detail

Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints

Recency Biased Causal Attention for Time-series Forecasting

FocusViT: Faithful Explanations for Vision Transformers via Gradient-Guided Layer-Skipping

Is Supervised Learning Really That Different from Unsupervised?

Confidence-Guided Self-Training for Gradual Domain Adaptation

Hyperbolic Part-Whole Image Segmentation

Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing

Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning

Understanding SAM's Robustness to Noisy Labels through Gradient Down-weighting

Predictive performance of power posteriors

Stochastic Bandits on Mixture Distributions: Metrics & Regret Bounds

Sparse Linear Bandits with Blocking Constraints

Neural Doubly Robust Proximal Causal Estimation

Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation

Policy Testing in Markov Decision Processes

Simplex-to-Euclidean Bijections for Categorical Flow Matching

From Counts to Preferences: Preference-Driven Models for Spatio-Temporal Event Data

From Restless to Contextual: A Thresholding Bandit Reformulation for Finite-horizon Improvement

SetPINNs: Set-based Physics-informed Neural Networks

Robust Learning of A Group DRO Neuron

From Transformers to State Spaces: GeoMamba-SE(3) for Fast and Accurate Molecular Learning

Empirically Calibrated Conditional Independence Tests

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information

Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning

Lloyd's $K$-Means Clustering Algorithm is Frank-Wolfe in Disguise

WSBD: Freezing-Based Optimizer for Quantum Neural Networks

Learning Right Monotone Permutation Matrices for Neural Subsequence Search

VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference

KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity

Regret Guarantees for Linear Contextual Stochastic Shortest Path

Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency Through Shuffling

Robustness and Generalization in Uncertainty-Aware Message Passing Neural Networks

Multilayer Correlation Clustering

Improving Adaptive Moment Optimization via Preconditioner Diagonalization

Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks

Adversarial Debiasing for Parameter Recovery

Securing Model Weights Against Eavesdropping Adversaries in Federated Learning Using Quantization

Variational Grey-Box Dynamics Matching

Local Regression on Path Spaces with Signature Metrics

Conformal Prediction in Hierarchical Classification with Constrained Representation Complexity

Consistent PCA and Spectral Clustering

On the hardness of Reinforcement Learning with Transition Lookahead

Frequency-Based Hyperparameter Selection in Games

i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data

Towards Motion-aware Referring Image Segmentation

Connectome-Guided Optimization for Deep Networks

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors

Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes

Closed-Form Coordinate Ascent Variational Inference for Student-t Process Regression with Student-t Likelihood

Unified Causal Discovery and Missing Data Imputation

Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect

Graphon Mixtures

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation

DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning

Identification and Estimation of "Probabilities of Causation" in the Presence of Confounding and Selection Bias

Settling the sample complexity of model-based offline reinforcement learning

Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning

Differential Privacy in Kernelized Contextual Bandits via Random Projections

High-Dimensional Spatial Autoregression with Latent Factors by Diversified Projections

On the eigenvalue decay rates of a class of neural-network related kernel functions defined on general domains

Longitudinal Flow Matching for Trajectory Modeling

Community-Enhanced Semi-seeded Network Alignment (CESSNA): A Robust Method with Application to Microbiome Networks

DAG-Informed Structure Learning from Multi-Dimensional Point Processes

AMRM-Pure: Semantic-Preserving Adversarial Purification

On the Finite-Sample Bias of Minimizing Expected Wasserstein Loss Between Empirical Distributions

Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures

Disentangling Federated Learning Heterogeneity: A Dual-Perspective Analysis of Quantifying Skew versus Scarcity

Meta-probabilistic Modeling

On the Bias of Variational Resampling

TESLA: Taylor Expansion of Sinusoidal Learnable Activations

Inference for Dispersion and Curvature of Random Objects

Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria

Preference-based Conditional Treatment Effects and Policy Learning

Bandit-based Maximum Inner Product Search with Data-Dependent Confidence Intervals

Loss Gaps Parity for Fairness in Heterogeneous Federated Learning

Open Multi-agent Multi-armed Bandit with Applications in Permissionless Blockchain

Loss-Driven Bayesian Active Learning

Learning Physical Operators using Neural Operators

In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning

Scalable Learning of Multivariate Distributions via Coresets

Ergodic and Subhomogeneous Dynamics in Hyperbolic Neural Networks

On the Role of Depth in the Expressivity of RNNs

MDPs with a State Sensing Cost

Counterfactual Explanations via Latent Structure for Time Series Classification

FastRank: Fast Tensor Rank Approximation based on Spectral Energy

Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

A Divergence-Based Method for Weighting and Averaging Model Predictions

Distribution free M-estimation

Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver

Optimal Variance and Covariance Estimation under Differential Privacy in the Add-Remove Model and Beyond

Non-Asymptotic Generalization and Optimization Bounds for Stochastic Gauss-Newton in Deep Neural Networks

Nonparametric Multi Change Point Detection for Markov Chains via Adaptive Clustering

Meta Sparse Principal Component Analysis

Meet Me at the Arm: The Cooperative Multi Armed Bandits Problem with Shareable Arms

Implicit Updates for Average-Reward Temporal Difference Learning

A Semi-Supervised Kernel Two-Sample Test

LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines

Gradient-Flow SDEs Have Unique Transient Population Dynamics

A Correlation Analysis Approach to Finding Interpretable Latent Representations via Conditional Generative Models

Rate optimal learning of equilibria from data

Hellinger Multimodal Variational Autoencoders

ConDiSim: Conditional Diffusion Models for Simulation-Based Inference

UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees

Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling

Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression

Optimal Local Convergence Rates of Stochastic First-Order Methods under Local Alpha-PL

Representation Learning via Non-Contrastive Mutual Information

On propagation of chaos for the Fisher-Rao gradient flow in entropic mean-field optimization

Shift is Good: Mismatched Data Mixing Improves Test Performance

Narrowing Action Choices with AI Improves Human Sequential Decisions

Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning

Deflated HeteroPCA: Overcoming the curse of ill-conditioning in heteroskedastic PCA

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory

Free Random Projection for In-Context Reinforcement Learning

Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix

Moonwalk: Inverse-Forward Differentiation

Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks

Structured Matrix Scaling for Multi-Class Calibration

E-Scores for (In)Correctness Assessment of Generative Model Outputs

On the calibration of survival models with competing risks

Learning Equivariant Functions via Quadratic Forms

Adversary-Free Counterfactual Prediction via Information-Regularized Representations

An Information-Geometric Approach to Artificial Curiosity

It’s All In The (Exponential) Family: An Equivalence Between Maximum Likelihood Estimation and Control Variates For Sketching Algorithms

Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients

Regularized Operator Extrapolation Method For Stochastic Hierarchical Variational Inequality Problems

Generalization Bounds for Spectral GNNs via Fourier Domain Analysis

Provable Accelerated Bayesian Optimization with Knowledge Transfer

A Polynomial-Time Approximation for Pairwise Fair $k$-Median Clustering

ZipMoE: A Theoretically-Grounded Mixture of Experts Approach forParameter-Efficient Deep Learning

Time-Aware Synthetic Control

Beyond Binary Out of Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories

Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games

CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks

Active Measurement of Two-Point Correlations

FlowPINNs: A Variational Framework for PDE Parameter Inference and Uncertainty Quantification

Statistical-computational gap in multiple Gaussian graph alignment

Multiclass Local Calibration with the Jensen-Shannon Distance

FedCCA: Federated Canonical Correlation Analysis

Near-optimal Rank Adaptive Inference of High Dimensional Matrices

Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale

Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting

Corruption Robust Thompson Sampling for Gaussian Bandits

Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples

On the Weight Density of L2-Regularized Linear Classification and Regression

Distributed estimation and inference for semiparametric binary response models

High Effort, Low Gain: Fundamental Limits of Active Learning for Linear Dynamical Systems

Transportability Without Graphs: A Bayesian Approach to Identifying s-Admissible Backdoor Sets

Linear Convergence of the Frank-Wolfe Algorithm over Product Polytopes

Formally Exploring Time-Series Anomaly Detection Evaluation Metrics

Fast Quasar-Convex Optimization with Constraints

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations

Bounds and Identification of Joint Probabilities of Potential Outcomes and Observed Variables under Monotonicity Assumptions

Generalized and Optimal Straight-Through Estimators

Sequential Off-Policy Learning with Logarithmic Smoothing

Efficient Logistic Regression with Mixture of Sigmoids

Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights

Busemann Functions in the Wasserstein Space: Existence, Closed-Forms, and Applications to Slicing

Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling

Beyond Binning: Soft Task Reformulation for Deep Regression

A Consequentialist Critique of Binary Classification Evaluation: Theory, Practice, and Tools

Finite-Time Analysis of Gradient Descent for Shallow Transformers

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent

Causal Additive Models with Unobserved Causal Paths and Backdoor Paths

ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models

Three-Step Nav: A Hierarchical Global–Local Planner for Zero-Shot Vision-and-Language Navigation

Denoising Score Matching with Random Features: Insights on Diffusion Models From Precise Learning Curves

A Bayesian Information-Theoretic Approach to Data Attribution

Discrete State Diffusion Models: A Sample Complexity Perspective

Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM

Training Latent Diffusion Models with Interacting Particle Algorithms

Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares

Differentially Private Clustering in Data Streams

Efficient and Accurate Tensor Compression via Recursive Sketching

High-Probability Bounds for Heterogeneous Local Differential Privacy

Empirical PAC-Bayes Bounds for Markov Chains

Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning

Structured Matching via Cost-Regularized Unbalanced Optimal Transport

Optimal Learning in Games under Delayed Feedback

Efficient Flow Matching using Latent Variables

Stationarity-Aware Causal Discovery in Time Series via Minimal Separating Sets

ACE-KT: Cascaded Cognitive Modeling for Stage-wise Knowledge Tracing

Graph Learning is Suboptimal in Causal Bandits

Fact-Augmented Lookahead Planning for LLM Agents

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks

Mask-Conditional Conformal Prediction: Valid Uncertainty For All Missing Data Mechanisms

Clustering-Based Edge Augmentation for Minimizing the Kirchhoff Index

Laplace approximation for Bayesian variable selection via Le Cam's one-step procedure

Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence

Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams

Deep Feedback Models

ECAI: Efficient Convolution Activation Inversion for Constant-Memory Convolutional Neural Networks Training

Boosted GFlowNets: Improving Exploration via Sequential Learning

Deformed Decomposition for Non-negative Tensors

On the Latent Information Geometry of the Grassmann Manifold

Scalable Model-Based Clustering with Sequential Monte Carlo

Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation

In-Context Function Learning in Large Language Models

A Goemans-Williamson type algorithm for identifying subcohorts in clinical trials

Incoherence in Goal-Conditioned Autoregressive Models

Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting

GiVA: Gradient-Informed Bases for Vector-Based Adaptation

Learning to Bid in Discriminatory Auctions with Budget Constraints

Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization

Tyler’s M-estimator Through the Lens Of Convex-Concave Programming

Towards Blackwell Optimality: Bellman Optimality Is All You Can Get

Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods

Convexified Message-Passing Graph Neural Networks

Minimizing Human Intervention in Online Classification

Boltzmann Exploration for Heavy-Tailed Bandits

An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations

Welfare-Centric Clustering

Active Measuring in Reinforcement Learning With Delayed Negative Effects

Efficient Uncoupled Learning Dynamics with $\tilde{O}\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback

LAMP: Extracting Local Decision Surfaces from Large Language Models

Quantifying Epistemic Uncertainty in Diffusion Models

On the Identifiability of Tensor Ranks via Prior Predictive Matching

Semi-Implicit Variational Inference via Kernelized Path Gradient Descent

Rethinking Intrinsic Dimension Estimation in Neural Representations

Partially Lazy Gradient Descent for Smoothed Online Learning

A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning

Probabilistic multi-dimensional classification with incomplete data at the prediction time

Counterfactual Credit Guided Bayesian Optimization

Unsupervised Ensemble Learning Through Deep Energy-based Models

Convergence of projected stochastic natural gradient variational inference for various step size and sample or batch size schedules

TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification

Design-Based Finite-Sample Analysis for Regression Adjustment

On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach

Understanding Generalization in Node and Link Prediction

Multi-Component VAE with Gaussian Markov Random Field

Happiness as a Measure of Fairness

Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension

Where You Place the Norm Matters: From Prejudiced to Neutral Initializations

Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity

Orientability of Causal Relations in Time Series using Summary Causal Graphs and Faithful Distributions

Dualformer: Time-Frequency Dual Domain Learning for Long-term Time Series Forecasting

Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints

A Scalable Lift-and-Project Differentiable Approach For the Maximum Cut Problem

When Can Federated Learning Match Centralized Learning? A PAC-Bayesian Generalization Gap Analysis

Secretary Problem with Predictions and Ordering

DeepRV: Accelerating Spatiotemporal Inference with Pre-trained Neural Priors

Differentially Private Minimum Spanning Tree in Euclidean Graphs

SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples

Off-policy Distributional Q($\lambda$): Distributional RL without Importance Sampling

RL-finetuning LLMs from on- and off-policy data with a single algorithm

Low-Rank Bias, Weight Decay, and Model Merging in Neural Networks

On Computational Limits of FlowAR Models: Expressivity and Efficiency

Noise-Free Dynamic Rank-Adaptation via Riemannian Methods in Federated Fine-Tuning

Enhancing LLM Safety through a Theoretical Minimax Game Lens

Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies from Simulated Nonparametric Functions

Robust Estimation of a Sparse Linear Model: Provable Guarantees with Non-convexity

Provable Guarantees for Estimating Covariances between Latent Variables with Application to Precision Matrix Estimation

Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration

Active learning for stochastic contextual linear bandits

FedDuA: Doubly Adaptive Federated Learning

Explanation Design in Strategic Learning: Sufficient Explanations That Induce Non-harmful Responses

Root Cause Analysis of Outliers in Unknown Cyclic Graphs

Harnessing the Power of Reinforcement Learning for Adaptive MCMC

Prior shift estimation for positive unlabeled data through the lens of kernel embedding

An Indicator of Membership Inference Security in Post-Training Quantized Models

Learning in Continuous State-Space MDPs for Network Inventory Management

Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids

Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independence

PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting

High-Dimensional Analysis of Bootstrap Ensemble Classifiers

Optimal rates for density and mode estimation with expand-and-sparsify representations

$k$-PCA for (non-squared) Euclidean Distances: Deterministic Polynomial Time Approximation

Rate-optimal Design for Anytime Best Arm Identification

Variance Constrained Distribution Alignment in Few-shot Models

Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes

Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity

Regularizing Extrapolation in Causal Inference

FIELDING: Clustered Federated Learning with Data Drift

Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes

Structural Alignment Improves Graph Test-Time Adaptation

Brenier Isotonic Regression

The Minimax Lower Bound of Kernel Stein Discrepancy Estimation

Spectral Clustering for Directed Graphs via Likelihood Estimation on Stochastic Block Models

The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks

Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity

Incorporating Expert Knowledge into Bayesian Causal Discovery of Mixtures of Directed Acyclic Graphs

Contraction rates for generalized posteriors based on $f$-divergences: a diffusion process approach

Information Hidden in Gradients of Regression with Target Noise

RoseCDL: Robust and Scalable Convolutional Dictionary Learning for rare-event and anomaly detection

A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback

Causal-DRF: Conditional Kernel Treatment Effect Estimation using Distributional Random Forest

Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks

On Different Notions of Redundancy in Conditional-Independence-Based Discovery of Graphical Models

Examining the Bias of In-Batch Sampling in Similarity Learning with Two-Tower Models

Weighted quantization using MMD: From mean field to mean shift using gradient flows

Sample Average Approximation for Alpha-Divergence Minimization with Exponential Convergence Guarantees

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective

Filter, Augment, Forecast: Online Data Selection for Robust Time Series Forecasting

A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm

On Relation-Aware Slicing in Cross-Domain Alignment

Preconditioned Attention: Enhancing Efficiency in Transformer Blocks

Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction

On Barycenter Computation: Analyzing Semi-Unbalanced Optimal Transport-based Method on Bures-Wasserstein manifold.

Causal Partial Identification via Conditional Optimal Transport

General Weighted Averaging in Stochastic Gradient Descent: CLT and Adaptive Optimality

Topological Alignment of Shared Vision-Language Embedding Space

A Pure Hypothesis Test for Inhomogeneous Random Graph Models Based on a Kernelised Stein Discrepancy

Efficient Learning of Stationary Diffusions with Stein-type Discrepancies

High-dimensional Learning with Noisy Labels

Improved Algorithms for Clustering with Noisy Distance Oracles

Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap

Catoni-Style Change Point Detection for Regret Minimization in Piecewise-Stationary Heavy-Tailed Bandits

High-dimensional Level Set Estimation with Trust Regions and Double Acquisition Functions

Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need

An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs

Influence Attributions can be Systematically Altered by Model Manipulation

Improving Coverage in Combined Prediction Sets with Weighted p-values

A Covering Framework for Offline POMDPs Learning Using Belief Space Metric

Low-Complexity and Consistent Graphon Estimation from Multiple Networks

Structured Difference-of-Q via Orthogonal Learning

From Guess2Graph: When and How Can Unreliable Experts Safely Boost Causal Discovery in Finite Samples?

Balanced and Robust Multi-Treatment Experimental Designs via Randomized Differencing

Sparse Linear Bandits with Fixed Sparsity Support: Adversarial and Stochastic Regimes

Tractable Uncertainty-Aware Meta-Learning

Random Features for Operator-Valued Kernels: Bridging Kernel Methods and Neural Operators

Efficient Subgroup Analysis via Optimal Trees with Global Parameter Fusion

Conformal Robust Control of Linear Systems

Feature Importance via Sets of Locally Performant Linear Models

Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks

ADOPT: Additive Optimal Transport Regression

Likelihood-Free Inference via Structured Score Matching

Duality-based Residual Estimation for Fully Offline Value-based Reinforcement Learning

On Kernel based Variational Autoencoders

LLMs Judging LLMs: A Simplex Perspective

Fair Clustering via Hierarchical Fair-Dirichlet Prior

Optimal Arm Elimination Algorithms for Combinatorial Bandits

MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation

SPIRE: Conditional Personalization for Federated Diffusion Generative Models

The Majority Vote Paradigm Shift: When Popular Meets Optimal

Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning

Sparse Offline Reinforcement Learning with Corruption Robustness

Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions

Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance

Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data

Sharp Risk Bounds for Early-stopping in Gaussian Linear Regression

Asymptotic optimality theory of confidence intervals of the mean

Hypergraph Neural Networks Accelerate MUS Enumeration

Corruption-robust Offline Multi-agent Reinforcement Learning from Human Feedback

Bad Values but Good Behavior: Learning Highly Misspecified Bandits with Function Approximation

Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation

Reinforcement Learning Using Known Invariances

AlphaFold's Bayesian Roots in Probability Kinematics

Minimax-Optimal Two-Sample Test with Sliced Wasserstein

Variational inference via radial transport

Thompson Sampling-like Algorithms for Stochastic Rising Bandits

Efficient Swap Regret Minimization in Combinatorial Bandits

Local Causal Discovery for Statistically Efficient Causal Inference

Differentially Private E-Values

Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning

Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variants

Conditional Flow Matching for Bayesian Posterior Inference

Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics

Partial VOROS: A Cost-aware Performance Metric for Binary Classifiers with Precision and Capacity Constraints

Active Subspaces in Infinite Dimension

Best Policy Learning from Trajectory Preference Feedback

Information-Theoretic Error Bounds for Source Localization in Neural Sensing

Incentivizing Truthful Submissions in a Data Marketplace for Mean Estimation

Semi-Random Noisy and One-Bit Matrix Completion via Nonconvex Optimization

Time Series Forecasting with Hahn Kolmogorov-Arnold Networks

Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards

Evaluation of Large Language Models via Coupled Token Generation

Bayesian Inverse Transition Learning: Learning Dynamics from Near-Optimal Trajectories

LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data

On the Misinformation in a Statistical Experiment

Undersmoothing Black-Box Models for Functional Estimation

Fundamental Limits of Non-Adaptive Group Testing With Markovian Correlation

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification

Towards Characterizing the Complexity of Riemannian Online Convex Optimization

The Role of Causal Features in Strategic Classification for Robustness and Alignment

Provably Efficient and Agile Randomized Q-Learning

Neuron Block Dynamics for XOR Classification with Zero-Margin

Where the Score Lives: A Wavelet View of Diffusion

From Token Imbalance to Balanced Routing: An ELBO-Regularized Probabilistic Framework for Contrastive Multimodal Learning

Conservative Inference in Switchback Experiments

On the optimal regret of collaborative personalized linear bandits

From Cells to Sentences: An End-to-End Framework for Table Understanding

Demystifying Transition Matching: When and Why It Can Beat Flow Matching

Generalized Correlation Shifting for Lasso

Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability

Learning Under Moral Hazard with Instrumental Regression and Generalized Method of Moments

Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approach

Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise

SiGHT: A Self-Supervised Graph-based Hallucination DeTection Framework for Domain-Specific LLMs

Towards Sensitivity-Aware Language Models

Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes

From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences

Three-operator splitting with stale gradients for faster non-linear optimal transport

Structured Temporal Inference in State-Space Models

Linear Reasoning Vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving

Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling

Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees

Hyperbolic Learning with Supervision from any Granularity

Statistical Inference for Explainable Boosting Machines

Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation

Online Learning-to-Defer with Varying Experts

Adversarial Robustness in One-Stage Learning-to-Defer

Faster Parallel MCMC: Metropolis Adjustment Is Best Served Warm

CTRLS: Chain-of-Thought Reasoning via Latent State-Transition

Partial Monotonicity for Submodular Maximization with a Knapsack Constraint

FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation

Power Transform Revisited: Numerically Stable, and Federated

Learning How Deep to Go: Self-Scaling Deep Reinforcement Learning

ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory

Gradient Regularized Natural Gradients

Data Distribution Valuation Using Generalized Bayesian Inference

Computationally lightweight classifiers with frequentist bounds on predictions

An Evaluation of Cost Functions for Algorithmic Recourse

GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression

Rank Lifting and Random Non-Linear Maps

Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees

Personalized Incentive Alignment: Correcting Utility-Driven Selection Bias in A/B Tests

Learning Geometry and Topology via Multi-Chart Flows

Representative, Informative, and De-Amplifying: Requirements for Robust Bayesian Active Learning under Model Misspecification

Tractable Shapley Values and Interactions via Tensor Networks

Provably Efficient Reinforcement Learning for Sparse Dynamical Systems with Non-Gaussian Noise

Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift

On the Convergence and Stability of Distributed Sub-model Training

Fast and Robust Simulation-Based Inference With Optimization Monte Carlo

The Rashomon Effect for Visualizing High-Dimensional Data

Lower Bounds for Public-Private Learning under Distribution Shift

Uncertainty Quantification for Named Entity Recognition via Conformal Prediction

Adaptive Coverage Policies in Conformal Prediction

Unmixing Mean Embeddings for Domain Adaptation with Target Label Proportion

Tight Analysis of Decentralized SGD: a Markov Chain Perspective

Near-Optimal Clustering in Mixture of Markov Chains

Zeroth-Order Stochastic Compositional Gradient Descent: Towards Black-Box Sparse AUC Maximization

A Geometric Approach to Optimal Experimental Design

Accelerating PDE Surrogates via RL-Guided Mesh Optimization

Accelerated Distributed Optimization with Compression and Error Feedback

Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs

Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification

Exact and Approximate MCMC for Doubly-intractable Probabilistic Graphical Models Leveraging the Underlying Independence Model

Hybrid Meta-Learners for Estimating Heterogeneous Treatment Effects

Kernel Treatment Effects with Adaptively Collected Data

Canopy Tree Height Estimation Using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing

Learnability with Partial Labels and Adaptive Nearest Neighbors

Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference

Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space

T$_k$CP: Context-Aware Pooling via Top-k% Activation Selection

Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction

Randomized HyperSteiner: A Stochastic Delaunay Triangulation Heuristic for the Hyperbolic Steiner Minimal Tree

Optimistic Reinforcement Learning with Quantile Objectives

TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer

Auto-Regressive Masked Diffusion Models

Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization

Multi-Armed Sampling Problem and the End of Exploration

Amortized Structural Variational Inference

Robust Federated Clustering under Heterogeneity and Adversaries

Auditing Pay-Per-Token in Large Language Models

Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning

Fast Private Adaptive Query Answering for Large Data Domains

Optimal Transport Guarantees to Nonparametric Regression for Locally Stationary Time Series

MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning

The Information Geometry of Local Generalization Dynamics

Private and Efficient Federated Statistical Learning

Black-Box Optimization from Small Offline Datasets via Meta Learning with Synthetic Tasks

A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks

Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts

Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners

Atlas-based Manifold Representations for Interpretable Riemannian Machine Learning

Deep Polynomial Chaos Expansion

Efficient Bilevel Optimization with KFAC-Based Hypergradients

CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning

Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization

Regression Descent: A Statistical Framework for Neural Network Optimization

Adaptive Diffusion Guidance via Stochastic Optimal Control

Calibrated Principal Component Regression

Functional Properties of the Focal-Entropy

Visual Prompting Reimagined: The Power of Activation Prompts

Inverse-Free Sparse Variational Gaussian Processes

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels

TexTSC: Class-Texture Preserving Data Condensation for Time Series Classification

Regularized $f-$Divergence Kernel Tests

Gradient Descent with Provably Tuned Learning-rate Schedules

Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

Retrieval Augmented Time Series Forecasting

The Cross-Context Threshold Test: Detecting Discrimination Under Environmental Shifts

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers

Replicable Machine Learning: Theory and Algorithms for Stochastic Convex and Non-Convex Optimization

SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning

LLM-as-a-Judge on a Budget

Scalable Policy Maximization Under Network Interference

A Unifying Framework for Unsupervised Concept Extraction

Nearly Optimal Best Arm Identification for Semiparametric Bandits

Multi-Agent Lipschitz Bandits

Policy Learning with Abstention

A New Perspective on Minimum-Norm Interpolation Under Gaussian Covariates

Efficient Model Performance Evaluation Using a Combination of Expert and Crowd-sourced Labels

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches

Direct Preference Optimization With Unobserved Preference Heterogeneity

Monotone and Conservative Policy Iteration Beyond the Tabular Case

Batch-Adaptive Causal Annotations

Learning Markov Processes as Sum-of-Square Forms for Analytical Belief Propagation

Slithering Through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging

CONTEXTUAL RANKING AND MATCHING. OPTIMAL REGRET UNDER LST

On the convergence and straightness of Rectified Flow

Learning Linear Regression with Low-Rank Tasks In-Context

RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics

Adaptive A/B Testing under Nonstationary Dynamics using State-Space Models

Counterfactually Fair Conformal Prediction

Two mathematical models of knowledge distillation

On the Hardness of Auditing Model Properties Under Updates: Complexity of Property-Preserving Updates

Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity

Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level

Accelerated Learning on Large-Scale Screens using Generative Library Models

Deliberate-When-Needed: Flow-Reasoner for Neuro-Symbolic Continuous Thought

Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs

The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving

TENDE: Transfer Entropy Neural Diffusion Estimation

CoreSPECT: Enhancing Clustering Algorithms via an Interplay of Density and Geometry

Differentially Private and Federated Structure Learning in Bayesian Networks

GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations

Exact Tensor Completion Beyond Isotropy and Invertibility

DRAUN: An Optimization-Agnostic Data Reconstruction Attack on Federated Unlearning

Predictive Deep Sets

Aggregation on Learnable Manifolds for Asynchronous Federated Optimisation

Provable FDR Control for Deep Feature Selection: Deep MLPs and Beyond

On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments

Bandits in Flux: Dynamic Regret under Adversarial Constraints

$\epsilon$-Identifiability of Causal Quantities

Numerical Fragility in Transformers: A Layer-wise Theory for Risk Estimation and Selective Stabilization

Generalization Bounds under Heavy-Tailed Losses

Bayesian Fourier Features for Reduced Rank Gaussian Processes

SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs

On the Neural Feature Ansatz for Deep Neural Networks

Learning to Explore with Lagrangians for Bandits under Unknown Constraints

PolarQuant: Vector Quantization with Polar Transformation

Optimized Projection-Free Algorithms for Online Learning: Construction and Worst-Case Analysis

How to Approximate Inference with Subtractive Mixture Models

Regularizing attention scores with bootstrapping

Beyond the Ideal: Analyzing the Inexact Muon Update

Network Inversion for Extreme-Case Training-Like Data Reconstruction

PowerSoftmax: Towards Secure LLM Inference Over Encrypted Data

Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism

Fundamental Limits for Weighted Empirical Approximations of Exponentially Tilted Distributions

Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics

Non-Stationary Functional Bilevel Optimization

BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization

Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models

Why is prompting hard? Understanding prompts on binary sequence predictors

Composable Coresets for Constrained Determinant Maximization and Beyond

Minimax Generalized Cross-Entropy

On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors

Learning Hyperparameters via a Data-Emphasized Variational Objective

On the Intrinsic Dimensions of Data in Kernel Learning

Support Basis: Fast Attention Beyond Bounded Entries

Rethinking Probabilistic Circuit Parameter Learning

PAC-Bayesian Bounds on Constrained $f$-Entropic Risk Measures

Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization

A projection-based framework for gradient-free and parallel learning

A Proof of Learning Rate Transfer under $\mu$P

DP-SPRT: Differentially Private Sequential Probability Ratio Tests

In-Context Learning for Discrete Optimal Transport: Can Transformers Sort?

Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls

Near Optimal Dropout-Robust Sortion

OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation

RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection

Beyond Pooling: Matching for Robust Generalization Under Data Heterogeneity

Dyno-Net: A Dynamic Feature Extraction Model for Gastrointestinal Polyp Detection

Practical and Efficient Rashomon Set Sampling for Model Interpretability

GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification

Policy-Oriented Binary Classification: Improving (KD-)CART Final Splits for Subpopulation Targeting

Differentially Private Algorithms for the Stochastic Compositional Optimization Problem

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps

Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees

One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow

Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators

BASTION: A Bayesian Framework for Trend and Seasonality Decomposition

Uncovering Hidden Training Dynamics in Neural Networks via Inter-Sample Influence Graphs

HGT-FD: Hypergraph transformer for Fraud Detection

High-Performance Self-Supervised Representation Learning by Joint Training of Flow Matching and Representation Encoder

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification

A Continuous Time Markov Chain Framework for Insertion Language Models

Beyond Real Data: Synthetic Data through the Lens of Regularization

Scalable Utility-Aware Multiclass Calibration

On the Number of Conditional Independence Tests in Constraint-based Causal Discovery

Panprediction: Optimal Predictions for Any Downstream Task and Loss

Orthogonal Representation Learning for Estimating Causal Quantities

Scalable community detection in massive networks via predictive assignment

Clustering risk in Non-parametric Hidden Markov and I.I.D. Models

Evidence Estimation in Gaussian Graphical Models Using a Telescoping Block Decomposition of the Precision Matrix

Graphical Model Inference with Erosely Measured Data

Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary

A new integrative learning framework for integrating multiple secondary outcomes into primary outcome analysis: a case study on liver health

Functional Integrative Bayesian Analysis of High-Dimensional Multiplatform Clinicogenomic Data

Revisiting RIP Guarantees for Sketching Operators on Mixture Models

Root cause discovery via permutations and Cholesky decomposition

Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods

Certifying Reading Comprehension in Large Language Models

Parameter-Free Dynamic Regret for Unconstrained Linear Bandits

Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games

A Modularized Framework for Piecewise-Stationary Restless Bandits

Pure Exploration with Infinite Answers

Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits

EventFlow: Forecasting Temporal Point Processes with Flow Matching

We Still Don’t Understand High-Dimensional Bayesian Optimization

Scalable resampling in massive generalized linear models via subsampled residual bootstrap

Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms