AISTATS 2025

583 papers

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis

Ruichen Luo, Sebastian U Stich, Samuel Horváth, Martin Takac

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

Kasimir Tanner, Matteo Vilucchio, Bruno Loureiro, Florent Krzakala

Time-series attribution maps with regularized contrastive learning

Steffen Schneider, Rodrigo González Laiz, Anastasiia Filippova, Markus Frey, Mackenzie W Mathis

Spectral Differential Network Analysis for High-Dimensional Time Series

Michael Hellstern, Byol Kim, Zaïd Harchaoui, Ali Shojaie

Variance-Dependent Regret Bounds for Nonstationary Linear Bandits

Zhiyong Wang, Jize Xie, Yi Chen, John C.S. Lui, Dongruo Zhou

Variation Due to Regularization Tractably Recovers Bayesian Deep Learning Uncertainty

James McInerney, Nathan Kallus

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

Jordan Penn, Lee M. Gunderson, Gecia Bravo-Hermsdorff, Ricardo Silva, David Watson

MDP Geometry, Normalization and Reward Balancing Solvers

Arsenii Mustafin, Aleksei Pakharev, Alex Olshevsky, Ioannis Paschalidis

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

Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro

Conditional Prediction ROC Bands for Graph Classification

Yujia Wu, Bo Yang, Elynn Chen, Yuzhou Chen, Zheshi Zheng

Zero-Shot Action Generalization with Limited Observations

Abdullah Alchihabi, Hanping Zhang, Yuhong Guo

Explaining ViTs Using Information Flow

Chase Walker, Md Rubel Ahmed, Sumit Kumar Jha, Rickard Ewetz

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

Sreejeet Maity, Aritra Mitra

Deep Optimal Sensor Placement for Black Box Stochastic Simulations

Paula Cordero Encinar, Tobias Schröder, Peter Yatsyshin, Andrew B. Duncan

From Gradient Clipping to Normalization for Heavy Tailed SGD

Florian Hübler, Ilyas Fatkhullin, Niao He

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

Saptarshi Chakraborty, Peter Bartlett

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

Alexandre Perez-Lebel, Gael Varoquaux, Sanmi Koyejo, Matthieu Doutreligne, Marine Le Morvan

On adaptivity and minimax optimality of two-sided nearest neighbors

Tathagata Sadhukhan, Manit Paul, Raaz Dwivedi

Conditional diffusions for amortized neural posterior estimation

Tianyu Chen, Vansh Bansal, James G. Scott

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

Ben Aoki-Sherwood, Catherine Bregou, David Liben-nowell, Kiran Tomlinson, Thomas Zeng

FLIPHAT: Joint Differential Privacy for High Dimensional Linear Bandits

Saptarshi Roy, Sunrit Chakraborty, Debabrota Basu

Robust Fair Clustering with Group Membership Uncertainty Sets

Sharmila Duppala, Juan Luque, John P Dickerson, Seyed A. Esmaeili

Fair Resource Allocation in Weakly Coupled Markov Decision Processes

Xiaohui Tu, Yossiri Adulyasak, Nima Akbarzadeh, Erick Delage

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

Xiaoxue Han, Huzefa Rangwala, Yue Ning

Near-Polynomially Competitive Active Logistic Regression

Yihan Zhou, Eric Price, Trung Nguyen

Learning from biased positive-unlabeled data via threshold calibration

Paweł Teisseyre, Timo Martens, Jessa Bekker, Jesse Davis

Credibility-Aware Multimodal Fusion Using Probabilistic Circuits

Sahil Sidheekh, Pranuthi Tenali, Saurabh Mathur, Erik Blasch, Kristian Kersting

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

Yilin Xie, Shiqiang Zhang, Joel Paulson, Calvin Tsay

A Subquadratic Time Approximation Algorithm for Individually Fair k-Center

Matthijs Ebbens, Nicole Funk, Jan Höckendorff, Christian Sohler, Vera Weil

Distributional Adversarial Loss

Saba Ahmadi, Siddharth Bhandari, Avrim Blum, Chen Dan, Prabhav Jain

Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning

Gianluca Drappo, Arnaud Robert, Marcello Restelli, Aldo A. Faisal, Alberto Maria Metelli

Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging

Amartya Banerjee, Harlin Lee, Nir Sharon, Caroline Moosmüller

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

Brian M Cho, Dominik Meier, Kyra Gan, Nathan Kallus

ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables

Sebastian Pineda Arango, Pedro Mercado, Shubham Kapoor, Abdul Fatir Ansari, Lorenzo Stella

Best-Arm Identification in Unimodal Bandits

Riccardo Poiani, Marc Jourdan, Emilie Kaufmann, Rémy Degenne

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

Yatin Dandi, Luca Pesce, Hugo Cui, Florent Krzakala, Yue Lu

Common Learning Constraints Alter Interpretations of Direct Preference Optimization

Lemin Kong, Xiangkun Hu, Tong He, David Wipf

Information-Theoretic Measures on Lattices for Higher-Order Interactions

Zhaolu Liu, Mauricio Barahona, Robert Peach

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

Arthur Pignet, Chiara Regniez, John Klein

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

Alexander Koebler, Thomas Decker, Ingo Thon, Volker Tresp, Florian Buettner

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

Sarbojit Roy, Malik Shahid Sultan, Tania Reyes Vallejo, Leena Ali Ibrahim, Hernando Ombao

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

Amartya Sanyal, Yaxi Hu, Yaodong Yu, Yian Ma, Yixin Wang

Tensor Network-Constrained Kernel Machines as Gaussian Processes

Frederiek Wesel, Kim Batselier

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

Sagnik Chatterjee, MANUJ MUKHERJEE, Alhad Sethi

A Causal Framework for Evaluating Deferring Systems

Filippo Palomba, Andrea Pugnana, Jose Manuel Alvarez, Salvatore Ruggieri

Disentangling Interactions and Dependencies in Feature Attributions

Gunnar König, Eric Günther, Ulrike Von Luxburg

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

Zhuorui Ye, Farzan Farnia

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

Ambrus Tamás, Szabolcs Szentpéteri, Balázs Csáji

Towards Fair Graph Learning without Demographic Information

Zichong Wang, Nhat Hoang, Xingyu Zhang, Kevin Bello, Xiangliang Zhang

Calibrated Computation-Aware Gaussian Processes

Disha Hegde, Mohamed Adil, Jon Cockayne

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

Corentin Pla, Maxime Vono, Hugo Richard

Robust Gradient Descent for Phase Retrieval

Alex Buna, Patrick Rebeschini

Computation-Aware Kalman Filtering and Smoothing

Marvin Pförtner, Jonathan Wenger, Jon Cockayne, Philipp Hennig

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

Marco Miani, Hrittik Roy, Søren Hauberg

The Sample Complexity of Stackelberg Games

Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

Active Bipartite Ranking with Smooth Posterior Distributions

James Cheshire, Stéphan Clémençon

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

Patrik Okanovic, Andreas Kirsch, Jannes Kasper, Torsten Hoefler, Andreas Krause

LMEraser: Large Model Unlearning via Adaptive Prompt Tuning

Jie Xu, Zihan Wu, Cong Wang, Xiaohua Jia

A Unified Evaluation Framework for Epistemic Predictions

Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Fabio Cuzzolin

Information-Theoretic Causal Discovery in Topological Order

Sascha Xu, Sarah Mameche, Jilles Vreeken

Implicit Diffusion: Efficient optimization through stochastic sampling

Pierre Marion, Anna Korba, Peter Bartlett, Mathieu Blondel, Valentin De Bortoli

Differentially Private Continual Release of Histograms and Related Queries

Monika Henzinger, A. R. Sricharan, Teresa Anna Steiner

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

Zhongxi Fang, Xun Su, Tomohisa Tabuchi, Jianming Huang, Hiroyuki Kasai

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

Tom Kempton, Stuart Burrell, Connor J Cheverall

Change Point Detection in Hadamard Spaces by Alternating Minimization

Anica Kostic, Vincent Runge, Charles Truong

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

Colin Dirren, Mattia Bianchi, Panagiotis D. Grontas, John Lygeros, Florian Dorfler

Multi-Agent Credit Assignment with Pretrained Language Models

Wenhao Li, Dan Qiao, Baoxiang Wang, Xiangfeng Wang, Wei Yin

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

Shirshendu Chatterjee, Soumendu Sundar Mukherjee, TAMOJIT SADHUKHAN

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

Benjamin Howson, Sarah Lucie Filippi, Ciara Pike-Burke

RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation

Yiming Wang, Yuxuan Song, Yiqun Wang, Minkai Xu, Rui Wang

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

Danial Dervovic, Michael Cashmore

Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation

Lucile Ter-Minassian, Liran Szlak, Ehud Karavani, Christopher C. Holmes, Yishai Shimoni

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

Jaiden Fairoze, Guillermo Ortiz-Jimenez, Mel Vecerik, Somesh Jha, Sven Gowal

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

Yusuke Tanaka, Takaharu Yaguchi, Tomoharu Iwata, Naonori Ueda

Partial Information Decomposition for Data Interpretability and Feature Selection

Charles Westphal, Stephen Hailes, Mirco Musolesi

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

Xiaoyan Hu, Ho-fung Leung, Farzan Farnia

Performative Prediction on Games and Mechanism Design

António Góis, Mehrnaz Mofakhami, Fernando P. Santos, Gauthier Gidel, Simon Lacoste-Julien

Approximating the Total Variation Distance between Gaussians

Arnab Bhattacharyya, Weiming Feng, Piyush Srivastava

Personalized Convolutional Dictionary Learning of Physiological Time Series

Axel Roques, Samuel Gruffaz, Kyurae Kim, Alain Oliviero Durmus, Laurent Oudre

Learning Graph Node Embeddings by Smooth Pair Sampling

Konstantin Kutzkov

The Hardness of Validating Observational Studies with Experimental Data

Jake Fawkes, Michael O’Riordan, Athanasios Vlontzos, Oriol Corcoll, Ciarán Mark Gilligan-Lee

Pure Exploration with Feedback Graphs

Alessio Russo, Yichen Song, Aldo Pacchiano

Factor Analysis with Correlated Topic Model for Multi-Modal Data

Małgorzata Łazęcka, Ewa Maria Szczurek

From Learning to Optimize to Learning Optimization Algorithms

Camille Castera, Peter Ochs

Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation

Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama

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

Aleksandar Armacki, Shuhua Yu, PRANAY SHARMA, Gauri Joshi, Dragana Bajovic

On Tractability of Learning Bayesian Networks with Ancestral Constraints

Juha Harviainen, Pekka Parviainen

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference

Dai Hai Nguyen, Tetsuya Sakurai, Hiroshi Mamitsuka

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

Nguyen Thang Loi, Duong Tan Loc, Vo Nguyen Le Duy

Adaptive RKHS Fourier Features for Compositional Gaussian Process Models

Xinxing Shi, Thomas Baldwin-McDonald, Mauricio A Álvarez

Consistent Amortized Clustering via Generative Flow Networks

Irit Chelly, Roy Uziel, Oren Freifeld, Ari Pakman

Truncated Inverse-Lévy Measure Representation of the Beta Process

Junyi Zhang, Angelos Dassios, Zhong Chong, Qiufei Yao

Post-processing for Fair Regression via Explainable SVD

Zhiqun Zuo, Ding Zhu, Mohammad Mahdi Khalili

Cross Validation for Correlated Data in Classification Models

Oren Yuval, Saharon Rosset

Bayesian Circular Regression with von Mises Quasi-Processes

Yarden Cohen, Alexandre Khae Wu Navarro, Jes Frellsen, Richard E. Turner, Raziel Riemer

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

Yufeng Zhang, Fengzhuo Zhang, Zhuoran Yang, Zhaoran Wang

A Likelihood Based Approach for Watermark Detection

Xingchi Li, Guanxun Li, Xianyang Zhang

AxlePro: Momentum-Accelerated Batched Training of Kernel Machines

Yiming Zhang, Parthe Pandit

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

Zifan Liu, Xinran Li, Shibo Chen, Gen Li, Jiashuo Jiang

Models That Are Interpretable But Not Transparent

Chudi Zhong, Panyu Chen, Cynthia Rudin