AISTATS 2026 Papers

Layout:

mini compact topic detail

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

Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity

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

Conformal Prediction in Hierarchical Classification with Constrained Representation Complexity

Conformal Robust Control of Linear Systems

Consistent PCA and Spectral Clustering

Causal Additive Models with Unobserved Causal Paths and Backdoor Paths

Empirical PAC-Bayes bounds for Markov chains

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

Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning

Enhancing LLM Safety through a Theoretical Minimax Game Lens

FedCCA: Federated Canonical Correlation Analysis

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent

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

Happiness as a Measure of Fairness

Active learning for stochastic contextual linear bandits

Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms

Identifiability of potentially degenerate Gaussian Mixture Models with piecewise affine mixing

Improving Semantic Uncertainty Quantification in Language Models via Token-Level Temperature Scaling

Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation

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

Adversarial Debiasing for Parameter Recovery

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

Distribution free M-estimation

Information Hidden in Gradients of Regression with Target Noise

On the convergence and straightness of flow matching models

A pure hypothesis test for inhomogeneous random graph models based on a kernelised Stein discrepancy

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

Low-Complexity and Consistent Graphon Estimation from Multiple Networks

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

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

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

Adaptive Diffusion Guidance via Stochastic Optimal Control

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

On Computational Limits of FlowAR Models: Expressivity and Efficiency

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

Preference-based Conditional Treatment Effects and Policy Learning

Graphon Mixtures

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

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

Rethinking Intrinsic Dimension Estimation in Neural Representations

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

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

Generalization Bounds for Heavy-Tailed Losses

Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes

ADOPT: Additive Optimal Transport Regression

Balanced and Robust Multi-Treatment Experimental Designs via Randomized Differencing

Inverse-Free Sparse Variational Gaussian Processes

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

Structural Alignment Improves Graph Test-Time Adaptation

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

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

Uncertainty-Aware Meta-Learning with Analytically Tractable Posterior

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

Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation

Variance Constrained Distribution Alignment in Few-shot Models

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

A Geometric Approach to Optimal Experimental Design

A Modularized Framework for Piecewise-Stationary Restless Bandits

Accelerating PDE Surrogates via RL-Guided Mesh Optimization

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

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

Adversarial Robustness in One-Stage Learning-to-Defer

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

AlphaFold's Bayesian Roots in Probability Kinematics

Regression Descent: A Statistical Framework for Neural Network Optimization

Boosted GFlowNets: Improving Exploration via Sequential Learning

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

Convexified Message-Passing Graph Neural Networks

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

An Evaluation of Cost Functions for Algorithmic Recourse

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

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

Conditional Flow Matching for Bayesian Posterior Sampling

Counterfactual Explanations via Latent Structure for Time Series Classification

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

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification

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

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

Power Transform Revisited: Numerically Stable, and Federated

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

Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization

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

Root cause analysis of outliers in unknown cyclic graphs

Fact-Augmented Lookahead for LLM Agents: Simple Online Memory, No Finetuning

PolarQuant: Vector Quantization with Polar Transformation

Formally Exploring Time-Series Anomaly Detection Evaluation Metrics

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

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

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

Generalized Correlation Shifting for Lasso

Corruption Robust Thompson Sampling for Gaussian Bandits

Rethinking Probabilistic Circuit Parameter Learning

Hybrid Meta-Learners for Estimating Heterogeneous Treatment Effects

Hyperbolic Part-Whole Image Segmentation

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

Incentivizing Truthful Submissions in a Data Marketplace for Mean Estimation

On Relation-Aware Slicing in Cross-Domain Alignment

Graph Learning is Suboptimal in Causal Bandits

Optimal Local Convergence Rates of Stochastic First-Order Methods under Local $\alpha$-PL

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

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

Learning Physical Operators using Neural Operators

Learning to Bid in Discriminatory Auctions with Budget Constraints

Policy Learning with Abstention

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

Direct Preference Optimization With Unobserved Preference Heterogeneity

Minimax-Optimal Two-Sample Test with Sliced Wasserstein

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

Neural Doubly Robust Proximal Causal Estimation

On the optimal regret of collaborative personalized linear bandits

SetPINNs: Set-based Physics-informed Neural Networks

Online Learning-to-Defer with Varying Experts

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

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

Partial Monotonicity for Submodular Maximization with a Knapsack Constraint

Gradient Regularized Natural Gradients

Hellinger Multimodal Variational Autoencoders

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

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

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

High-Dimensional Analysis of Bootstrap Ensemble Classifiers

Rashomon Effect for Visualizing High-Dimensional Data

FIELDING: Clustered Federated Learning with Data Drift

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

Recency Biased Causal Attention for Time-series Forecasting

Near-optimal Rank Adaptive Inference of High Dimensional Matrices

Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning

Clustering in Mixtures of Ergodic Markov Chains: Fundamental Limit and Two-Stage Algorithm

Deformed Decomposition for Non-negative Tensors

Reinforcement Learning Using Known Invariances

Semi-Random Noisy and One-Bit Matrix Completion With Nonconvex Primal-Dual Framework

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

Sequential Off-Policy Learning with Logarithmic Smoothing

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

Improving Coverage in Combined Prediction Sets with Weighted p-values

Minimax generalized cross-entropy

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

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

Time Series Forecasting with Hahn Kolmogorov-Arnold Networks

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

Fast Quasar-Convex Optimization with Constraints

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

Towards Blackwell Optimality: Bellman Optimality Is All You Can Get

Linear Convergence of the Frank-Wolfe Algorithm over Product Polytopes

Towards Sensitivity-Aware Language Models

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

Time-series Diagnostic Reasoning with Knowledge Injection

Network Inversion for Extreme-Case Training-Like Data Reconstruction

Training Latent Diffusion Models with Interacting Particle Algorithms

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

Structured Temporal Inference in State-Space Models

Undersmoothing Black-Box Models for Functional Estimation

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

Faster parallel MCMC: Metropolis adjustment is best served warm

Understanding and Steering Large Generative Models Using Constitutions for Atomic Concept Edits

Where the Score Lives: A Wavelet View of Diffusion

Why is prompting hard? Understanding prompts on binary sequence predictors

A New Perspective on Least-Norm Interpolation Under Gaussian Covariates

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

A Semi-Supervised Kernel Two-Sample Test

A Unifying Framework for Unsupervised Concept Extraction

Gradient-flow SDEs have unique transient population dynamics

Support Basis: Fast Attention Beyond Bounded Entries

Active Measuring in Reinforcement Learning With Delayed Negative Effects

Adversary-Free Counterfactual Prediction via Information-Regularized Representations

An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representation

Information-theoretic error bounds for source localization in neural sensing

Refining Covariance Matrix Estimation in Stochastic Gradient Descent through Bias Reduction

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

Auto-Regressive Masked Diffusion Models

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

Bandits in Flux: Dynamic Regret under Adversarial Constraints

On the Misinformation in a Statistical Experiment

BASTION: A Bayesian Framework for Trend and Seasonality Decomposition

Bayesian Fourier Features for Reduced Rank Gaussian Processes

Beyond Real Data: Synthetic Data through the Lens of Regularization

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

Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning

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

CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks

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

Optimistic Actor-Critic with Parametric Policies: Unifying Sample Efficiency and Practicality

Deep Polynomial Chaos Expansion

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

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Text-Guided Generative AI Models

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

Deep Feedback Models

Provable Accelerated Bayesian Optimization with Knowledge Transfer

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

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

Differentially Private and Federated Structure Learning in Bayesian Networks

Low-rank bias, weight decay, and model merging in neural networks

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

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

Efficient Bilevel Optimization with KFAC-Based Hypergradients

Efficient Flow Matching using Latent Variables

The Majority Vote Paradigm Shift: When Popular Meets Optimal

Efficient model performance evaluation using a combination of expert and crowd-sourced labels

Empirically Calibrated Conditional Independence Tests

Finite-Time Analysis of Gradient Descent for Shallow Transformers

Rank Lifting and Random Non-Linear Maps

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

Functional Properties of the Focal-Entropy

Towards Characterizing the Complexity of Riemannian Online Convex Optimization

Fundamental limits for weighted empirical approximations of exponentially tilted distributions

Frequency-Based Hyperparameter Selection in Games

Free Random Projection for In-Context Reinforcement Learning

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

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

Representation Learning via Non-Contrastive Mutual Information

High-Probability Bounds for Heterogeneous Local Differential Privacy

On the Role of Depth in the Expressivity of RNNs

AMRM-Pure: Semantic-Preserving Adversarial Purification

How to approximate inference with subtractive mixture models

Likelihood-Free Inference via Structured Score Matching

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

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

Is Supervised Learning Really That Different from Unsupervised?

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

Learning Equivariant Functions via Quadratic Forms

FedDuA: Doubly Adaptive Federated Learning

$\epsilon$-Identifiability of Causal Quantities

Causal Partial Identification via Conditional Optimal Transport

Learning Linear Regression with Low-Rank Tasks in-Context

Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale

Meta-probabilistic Modeling

Statistical Inference for Explainable Boosting Machines

Confidence-Guided Self-Training for Domain Adaptation

Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions

Monotone and Conservative Policy Iteration Beyond the Tabular Case

Rate optimal learning of equilibria from data

Understanding Generalization in Node and Link Prediction

Best Policy Learning from Trajectory Preference Feedback

Multi-Agent Lipschitz Bandits

Multi-Armed Sampling Problem and the End of Exploration

Multiclass Local Calibration with the Jensen-Shannon Distance

Nearly Optimal Best Arm Identification for Semiparametric Bandits

Numerical Fragility in Transformers: A Layer-wise Theory for Explaining, Forecasting, and Mitigating Instability

Hypergraph Neural Networks Accelerate MUS Enumeration

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

Securing Model Weights against Eavesdropping Adversaries in Federated Learning using Quantization

Private, Efficient, and Robust Federated Statistical Learning

Bayesian Model Selection via a Data-Emphasized Variational Objective

On the Latent Information Geometry of the Grassmann Manifold

Differential Privacy in Kernelized Contextual Bandits via Random Projections

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

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

On the calibration of survival models with competing risks

Regret Guarantees for Linear Contextual Stochastic Shortest Path

Hyperbolic Learning with Supervision from any Granularity

DP-SPRT: Differentially Private Sequential Probability Ratio Tests

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

On the Neural Feature Ansatz for Deep Neural Networks

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

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations

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

Optimal Transport Guarantees to Nonparametric Regression for Locally Stationary Time Series

Optimistic Reinforcement Learning with Quantile Objectives

Optimized projection-free algorithms for online learning: construction and worst-case analysis

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

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

Differentially Private Algorithms for the Stochastic Compositional Optimization Problem

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

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

Regularizing Extrapolation in Causal Inference

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

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

Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

PowerSoftmax: Towards Secure LLM Inference Over Encrypted Data

Predictive Deep Sets

EventFlow: Forecasting Temporal Point Processes with Flow Matching

Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors

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

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

Provable FDR Control for Deep Feature Selection: Arbitrarily Deep MLPs and Transformers

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

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

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

Quantifying Epistemic Uncertainty in Diffusion Models

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

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

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

Optimal Arm Elimination Algorithms for Combinatorial Bandits

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

Regularized $f-$Divergence Kernel Tests

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

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

Structured Matching via Cost-Regularized Unbalanced Optimal Transport

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

Robust Federated Clustering under Heterogeneity and Adversaries

Ergodic and Subhomogeneous Dynamics in Hyperbolic Neural Networks

Robust Learning of A Group DRO Neuron

Robustness and Generalization in Uncertainty-Aware Message Passing Neural Networks

Data Distribution Valuation Using Generalized Bayesian Inference

Scalable Policy Maximization Under Network Interference

Scalable Utility-Aware Multiclass Calibration

Simplex-to-Euclidean Bijections for Categorical Flow Matching

Slithering through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging

TESLA: Taylor Expansion of Sinusoidal Learnable Activations

Efficient Logistic Regression with Mixture of Sigmoids

Counterfactual Credit Guided Bayesian Optimization

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

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

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches

Improved Algorithms for Clustering with Noisy Distance Oracles

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

Secretary problem with predictions and ordering

Parameter-Free Dynamic Regret for Unconstrained Linear Bandits

Thompson Sampling-like Algorithms for Stochastic Rising Bandits

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

Variational inference via radial transport

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

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

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

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

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

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

Discrete State Diffusion Models: A Sample Complexity Perspective

WSBD: Freezing-Based Optimizer for Quantum Neural Networks

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

Near Optimal Dropout-Robust Sortion

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

Auditing Pay-Per-Token in Large Language Models

Visual Prompting Reimagined: The Power of Activation Prompts

Narrowing Action Choices with AI Improves Human Sequential Decisions

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

Differentially Private Clustering in Data Streams

Boltzmann Exploration for Heavy-Tailed Bandits

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

Composable Coresets for Constrained Determinant Maximization and Beyond

Scalable Learning of Multivariate Distributions via Coresets

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

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

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

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

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

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

Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs

Uncertainty Quantification for Named Entity Recognition via Conformal Prediction

Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees

Clustering-Based Edge Augmentation for Minimizing the Kirchhoff Index

Regularized Operator Extrapolation Method For Stochastic Bilevel Variational Inequality Problems

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

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

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

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

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

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

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

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

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

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

The Minimax Lower Bound of Kernel Stein Discrepancy Estimation

Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization

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

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

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

Counterfactually Fair Conformal Prediction

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

Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints

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

Rate-optimal Design for Anytime Best Arm Identification

On Kernel based Variational Autoencoders

Fast and Robust Simulation-Based Inference With Optimization Monte Carlo

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

Topological Alignment of Shared Vision-Language Embedding Space

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

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

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

Unified Causal Discovery and Missing Data Imputation

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

LAMP: Extracting Local Decision Surfaces from Large Language Models

Local Regression on Path Spaces with Signature Metrics

Towards Motion-aware Referring Image Segmentation

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

Adaptive Coverage Policies in Conformal Prediction

Beyond the Ideal: Analyzing the Inexact Muon Update

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

Certifying Reading Comprehension in Large Language Models

Structured Matrix Scaling for Multi-Class Calibration

Kernel Treatment Effects with Adaptively Collected Data

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

Differentially Private Minimum Spanning Tree in Euclidean Graphs

Differentially Private E-Values

Longitudinal Flow Matching for Trajectory Modeling

Evaluation of Large Language Models via Coupled Token Generation

We Still Don’t Understand High-Dimensional Bayesian Optimization

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

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

Computationally Lightweight Classifiers with Frequentist Bounds on Prediction Errors

Minimizing Human Intervention in Online Classification

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

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

TENDE: Transfer Entropy Neural Diffusion Estimation

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

On the Intrinsic Dimensions of Data in Kernel Learning

Connectome-Guided Optimization for Deep Networks

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

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

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

Design-Based Finite-Sample Analysis for Regression Adjustment

Generalization Bounds for Spectral GNNs via Fourier Domain Analysis

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

A correlation analysis approach to finding interpretable latent representations via conditional generative models

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

Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance

FastRank: Fast Tensor Rank Approximation based on Spectral Energy

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

Convergence of projected stochastic natural gradient variational inference: Balancing speed, computational effort, and accuracy

Model-independent O(1/k)-convergence rate for TD(0) with linear function approximation, universal learning steps and i.i.d. samples

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

Beyond Binning: Soft Task Reformulation for Deep Regression

A Continuous Time Markov Chain Framework for Insertion Language Models

Panprediction: Optimal Predictions for Any Downstream Task and Loss

An Information-Geometric Approach to Artificial Curiosity

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

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

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

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

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

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

Pure Exploration with Infinite Answers

Generalized and Optimal Straight-Through Estimators

Orthogonal Representation Learning for Estimating Causal Quantities

OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation

Standard Acquisition is Sufficient for Asynchronous Bayesian Optimization

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

GiVA: Gradient-Informed Bases for Vector-Based Adaptation

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

Semi-Implicit Variational Inference via Kernelized Path Gradient Descent

Partially Lazy Gradient Descent for Smoothed Online Learning

A Regularized Actor-Critic Algorithm for Bi-Level Reinforcement Learning

On the hardness of Reinforcement Learning with Transition Lookahead

Unsupervised Ensemble Learning Through Deep Energy-based Models

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

Multi-Component VAE with Gaussian Markov Random Field

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

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

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

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

Practical Attribution Guidance for Rashomon Sets

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

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

DeepRV: Accelerating spatiotemporal inference with pre-trained neural priors

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

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

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

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

Meta Sparse Principal Component Analysis

Policy Testing in Markov Decision Processes

Harnessing the Power of Reinforcement Learning for Adaptive MCMC

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

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

Learning in Continuous State-Space MDPs for Network Inventory Management

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

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

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

Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes

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

Brenier Isotonic Regression

The Riemannian Geometry associated to Gradient Flows of Linear Convolutional Networks

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

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

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

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

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

Stochastic Bandits on Mixture Distributions: Metrics & Regret Bounds

Sparse Linear Bandits with Blocking Constraints

Preconditioned Attention: Enhancing Efficiency in Transformer Blocks

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

Efficient Learning of Stationary Diffusions with Stein-type Discrepancies

High-dimensional Learning with Noisy Labels

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

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

Influence Attributions can be Systematically Altered by Model Manipulation

A Covering Framework for Offline POMDPs Learning using Belief Space Metric

Structured Difference-of-Q via Orthogonal Learning

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

Efficient Subgroup Analysis via Optimal Trees with Global Parameter Fusion

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

Feature Importance via Sets of Locally Performant Linear Models

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

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

LLMs Judging LLMs: A Simplex Perspective

Fair Clustering via Hierarchical Fair-Dirichlet Prior

MDPs with a State Sensing Cost

SPIRE: Conditional Personalization for Federated Diffusion Generative Models

Implicit Updates for Average-Reward Temporal Difference Learning

Welfare-Centric Clustering

Sparse Offline Reinforcement Learning with Corruption Robustness

Sharp risk bounds for early-stopping in Gaussian linear regression

Asymptotic optimality theory of confidence intervals of the mean

A Divergence-Based Method for Weighting and Averaging Model Predictions

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

A Bayesian Information-Theoretic Approach to Data Attribution

Near-Optimal Swap Regret in Combinatorial Bandits

Local Causal Discovery for Statistically Efficient Causal Inference

Efficient and Accurate Tensor Compression via Recursive Sketching

Active Subspaces in Infinite Dimension

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

Time-Aware Synthetic Control

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

Nonparametric Multi Change Point Detection for Markov Chains via Adaptive Clustering

Fundamental Limits of Non-Adaptive Group Testing With Markovian Correlation

Moonwalk: Inverse-Forward Differentiation

Provably Efficient and Agile Randomized Q-Learning

Neuron Block Dynamics for XOR Classification with Zero-Margin

Conservative Inference in Switchback Experiments

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

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

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

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

Incoherence in goal-conditioned autoregressive models

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

FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation

Variational Grey-Box Dynamics Matching

Multilayer Correlation Clustering

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

Learning Geometry and Topology via Multi-Chart Flows

In-Context Function Learning in Large Language Models

Tractable Shapley Values and Interactions via Tensor Networks

Statistical-computational gap in multiple Gaussian graph alignment

Lower Bounds for Public-Private Learning under Distribution Shift

Unmixing Mean Embeddings for Domain Adaptation with Target Label Proportion

Tight Analysis of Decentralized SGD: a Markov Chain Perspective

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

Accelerated Distributed Optimization with Compression and Error Feedback

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

Learnability with partial labels and adaptive nearest neighbors

Loss Gaps Parity for Fairness in Heterogeneous Federated Learning

Scalable Model-Based Clustering with Sequential Monte Carlo

TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer

Amortized Structural Variational Inference

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

Fast Private Adaptive Query Answering for Large Data Domains

MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning

The Information Geometry of Local Generalization Dynamics

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

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

ConDiSim: Conditional Diffusion Models for Simulation-Based Inference

Atlas-based Manifold Representations for Interpretable Riemannian Machine Learning

Learning Right Monotone Permutation Matrices for Neural Subsequence Search

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

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

Active Measurement of Two-Point Correlations

Calibrated Principal Component Regression

Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels

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

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

Gradient Descent with Provably Tuned Learning-rate Schedules

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

Retrieval Augmented Time Series Forecasting

Improving Adaptive Moment Optimization via Preconditioner Diagonalization

LLM-as-a-Judge on a Budget

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

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

Batch-Adaptive Causal Annotations

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

Contextual ranking and matching. Optimal regret under LST

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

Shift is Good: Mismatched Data Mixing Improves Test Performance

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

Two mathematical models of knowledge distillation

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

Accelerated Learning on Large Scale Screens using Generative Library Models

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

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

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

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

Exact Tensor Completion Powered by Slim Transforms

Aggregation on Learnable Manifolds for Asynchronous Federated Optimisation

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

HGT-FD: Hypergraph transformer for Fraud Detection

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

On the Identifiability of Tensor Ranks via Prior Predictive Matching

Learning to Explore with Lagrangians for Bandits under Unknown Constraints

From Decision to Acquisition: Loss-Driven Bayesian Active Learning

Regularizing attention scores with the bootstrapping

On the bias of variational resampling

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

Optimal Learning in Two-Player Zero-Sum Games under Delayed Feedback

Non-Stationary Functional Bilevel Optimization

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

On the Convergence and Stability of Distributed Sub-model Training