AISTATS 2025

583 papers

Multi-agent Multi-armed Bandit Regret Complexity and Optimality

Mengfan Xu, Diego Klabjan

Training LLMs with MXFP4

Albert Tseng, Tao Yu, Youngsuk Park

Towards a mathematical theory for consistency training in diffusion models

Gen Li, Zhihan Huang, Yuting Wei

Clustered Invariant Risk Minimization

Tomoya Murata, Atsushi Nitanda, Taiji Suzuki

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

Kevin Luo, Yufan Li, Pragya Sur

Dissecting the Impact of Model Misspecification in Data-Driven Optimization

Adam N. Elmachtoub, Henry Lam, Haixiang Lan, Haofeng Zhang

Minimum Empirical Divergence for Sub-Gaussian Linear Bandits

Kapilan Balagopalan, Kwang-Sung Jun

Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation

Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, Yasuhiro Fujiwara

Neural Point Processes for Pixel-wise Regression

Chengzhi Shi, Gözde Özcan, Miquel Sirera Perelló, Yuanyuan Li, Nina Iftikhar Shamsi

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

Xiangyu Chang, Yingcong Li, Muti Kara, Samet Oymak, Amit Roy-Chowdhury

Improved dependence on coherence in eigenvector and eigenvalue estimation error bounds

Hao Yan, Keith Levin

Multi-Player Approaches for Dueling Bandits

Or Raveh, Junya Honda, Masashi Sugiyama

Transformers are Provably Optimal In-context Estimators for Wireless Communications

Vishnu Teja Kunde, Vicram Rajagopalan, Chandra Shekhara Kaushik Valmeekam, Krishna Narayanan, Jean-Francois Chamberland

On the Inherent Privacy of Zeroth-Order Projected Gradient Descent

Devansh Gupta, Meisam Razaviyayn, Vatsal Sharan

An Adaptive Method for Weak Supervision with Drifting Data

Alessio Mazzetto, Reza Esfandiarpoor, Akash Singirikonda, Eli Upfal, Stephen Bach

Differentially Private Range Queries with Correlated Input Perturbation

Prathamesh Dharangutte, Jie Gao, Ruobin Gong, Guanyang Wang

Dynamic DBSCAN with Euler Tour Sequences

Seiyun Shin, Ilan Shomorony, Peter Macgregor

On Distributional Discrepancy for Experimental Design with General Assignment Probabilities

Anup Rao, Peng Zhang

Fully Dynamic Adversarially Robust Correlation Clustering in Polylogarithmic Update Time

Vladimir braverman, Prathamesh Dharangutte, Shreyas Pai, Vihan Shah, Chen Wang

Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization

Ziwei Su, Diego Klabjan

Learning to Negotiate via Voluntary Commitment

Shuhui Zhu, Baoxiang Wang, Sriram Ganapathi Subramanian, Pascal Poupart

Adaptive Convergence Rates for Log-Concave Maximum Likelihood

Gil Kur, Aditya Guntuboyina

Improving Stochastic Cubic Newton with Momentum

El Mahdi Chayti, Nikita Doikov, Martin Jaggi

Recursive Learning of Asymptotic Variational Objectives

Alessandro Mastrototaro, Mathias Müller, Jimmy Olsson

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

Jake Fawkes, Lucile Ter-Minassian, Desi R. Ivanova, Uri Shalit, Christopher C. Holmes

Differentially private algorithms for linear queries via stochastic convex optimization

Giorgio Micali, Clement LEZANE, Annika Betken

A Shared Low-Rank Adaptation Approach to Personalized RLHF

Renpu Liu, Peng Wang, Donghao Li, Cong Shen, Jing Yang

Rate of Model Collapse in Recursive Training

Ananda Theertha Suresh, Andrew Thangaraj, Aditya Nanda Kishore Khandavally

Proximal Sampler with Adaptive Step Size

Bo Yuan, Jiaojiao Fan, Jiaming Liang, Yongxin Chen

MEDUSA: Medical Data Under Shadow Attacks via Hybrid Model Inversion

Asfandyar Azhar, Paul Thielen, Curtis Langlotz

The VampPrior Mixture Model

Andrew A. Stirn, David A. Knowles

Integer Programming Based Methods and Heuristics for Causal Graph Learning

Sanjeeb Dash, Joao Goncalves, Tian Gao

Axiomatic Explainer Globalness via Optimal Transport

Davin Hill, Joshua Bone, Aria Masoomi, Max Torop, Jennifer Dy

UNHaP: Unmixing Noise from Hawkes Processes

Virginie Loison, Guillaume Staerman, Thomas Moreau

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

Peyman Morteza

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

Kun Zhao, Jiayi Wang, Yifei Lou

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

Safwan Labbi, Daniil Tiapkin, Lorenzo Mancini, Paul Mangold, Eric Moulines

Optimal downsampling for Imbalanced Classification with Generalized Linear Models

Yan Chen, Jose Blanchet, Krzysztof Dembczynski, Laura Fee Nern, Aaron Eliasib Flores

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

Leonardo Bianco, Christine Keribin, Zacharie Naulet

Sequential Kernelized Stein Discrepancy

Diego Martinez-Taboada, Aaditya Ramdas

MING: A Functional Approach to Learning Molecular Generative Models

Van Khoa Nguyen, Maciej Falkiewicz, Giangiacomo Mercatali, Alexandros Kalousis

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

Nithish Suresh Babu, Ritesh Kumar, Shashank Vatedka

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

Francesco Saverio Pezzicoli, Valentina Ros, François P. Landes, Marco Baity-Jesi

Parameter estimation in state space models using particle importance sampling

Yuxiong Gao, Wentao Li, Rong Chen

On the Relationship Between Robustness and Expressivity of Graph Neural Networks

Lorenz Kummer, Wilfried N. Gansterer, Nils Morten Kriege

Robust Score Matching

Richard Schwank, Andrew McCormack, Mathias Drton

A primer on linear classification with missing data

Angel David REYERO LOBO, Alexis Ayme, Claire Boyer, Erwan Scornet

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

Guillaume Braun, Minh Ha Quang, Masaaki Imaizumi

Efficient Optimization Algorithms for Linear Adversarial Training

Antônio H. Ribeiro, Thomas B. Schön, Dave Zachariah, Francis Bach

posteriordb: Testing, Benchmarking and Developing Bayesian Inference Algorithms

Måns Magnusson, Jakob Torgander, Paul-Christian Bürkner, Lu Zhang, Bob Carpenter

Bandit Pareto Set Identification in a Multi-Output Linear Model

Cyrille KONE, Emilie Kaufmann, Laura Richert

Evaluating Prediction-based Interventions with Human Decision Makers In Mind

Inioluwa Deborah Raji, Lydia T. Liu

Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks

Ashwin Samudre, Mircea Petrache, Brian Nord, Shubhendu Trivedi

Optimal Multi-Objective Best Arm Identification with Fixed Confidence

Zhirui Chen, P. N. Karthik, Yeow Meng Chee, Vincent Y. F. Tan

Variational Inference on the Boolean Hypercube with the Quantum Entropy

Eliot Beyler, Francis Bach

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

Jiaqi Han, Mingjian Jiang, Yuxuan Song, Stefano Ermon, Minkai Xu

Distributional Counterfactual Explanations With Optimal Transport

Lei You, Lele Cao, Mattias Nilsson, Bo Zhao, Lei Lei

Model selection for behavioral learning data and applications to contextual bandits

Julien Aubert, Louis Köhler, Luc Lehéricy, Giulia Mezzadri, Patricia Reynaud-Bouret

Policy Teaching via Data Poisoning in Learning from Human Preferences

Andi Nika, Jonathan Nöther, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla

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

Taole Sha, Michael Minyi Zhang

Locally Optimal Descent for Dynamic Stepsize Scheduling

Gilad Yehudai, Alon Cohen, Amit Daniely, Yoel Drori, Tomer Koren

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

Yuxin Wang, Botian Jiang, Yiran Guo, Quan Gan, David Wipf

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

Dun Zeng, Zenglin Xu, SHIYU LIU, Yu Pan, Qifan Wang

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

Elena Grigorescu, Young-San Lin, Maoyuan Song

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

Zijun Gao

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

Chengrui Qu, Laixi Shi, Kishan Panaganti, Pengcheng You, Adam Wierman

Bayesian Decision Theory on Decision Trees: Uncertainty Evaluation and Interpretability

Yuta Nakahara, Shota Saito, Naoki Ichijo, Koki Kazama, Toshiyasu Matsushima

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

Kenghao Zheng, Zi Long, Shuxin Wang

Q-function Decomposition with Intervention Semantics for Factored Action Spaces

Junkyu Lee, Tian Gao, Elliot Nelson, Miao Liu, Debarun Bhattacharjya

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

Xingzhi Sun, Danqi Liao, Kincaid MacDonald, Yanlei Zhang, Guillaume Huguet

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

Xuefeng GAO, Lingjiong Zhu

Pareto Set Identification With Posterior Sampling

Cyrille KONE, Marc Jourdan, Emilie Kaufmann

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

Nima Akbarzadeh, Yossiri Adulyasak, Erick Delage

Optimizing Neural Network Training and Quantization with Rooted Logistic Objectives

Zhu Wang, Praveen Raj Veluswami, Harsh Mishra, Sathya N. Ravi

Learning the Distribution Map in Reverse Causal Performative Prediction

Daniele Bracale, Subha Maity, Yuekai Sun, Moulinath Banerjee

Type Information-Assisted Self-Supervised Knowledge Graph Denoising

Jiaqi Sun, Yujia Zheng, Xinshuai Dong, Haoyue Dai, Kun Zhang

Distance Estimation for High-Dimensional Discrete Distributions

Kuldeep S. Meel, Gunjan Kumar, Yash Pote

Balls-and-Bins Sampling for DP-SGD

Lynn Chua, Badih Ghazi, Charlie Harrison, Pritish Kamath, Ravi Kumar

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

Yingqian Cui, Jie Ren, Pengfei He, Hui LIU, Jiliang Tang

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

Keyue Jiang, Bohan Tang, Xiaowen Dong, Laura Toni

Microfoundation inference for strategic prediction

Daniele Bracale, Subha Maity, Felipe Maia Polo, Seamus Somerstep, Moulinath Banerjee

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

Suqi Liu, Morgane Austern

Fundamental Limits of Perfect Concept Erasure

Somnath Basu Roy Chowdhury, Kumar Avinava Dubey, Ahmad Beirami, Rahul Kidambi, Nicholas Monath

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

Róbert István Busa-Fekete, Umar Syed

Poisoning Bayesian Inference via Data Deletion and Replication

Matthieu Carreau, Roi Naveiro, William N. Caballero

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

Aya Kayal, Sattar Vakili, Laura Toni, Alberto Bernacchia

Global Group Fairness in Federated Learning via Function Tracking

Yves Rychener, Daniel Kuhn, Yifan Hu

Entropic Matching for Expectation Propagation of Markov Jump Processes

Yannick Eich, Bastian Alt, Heinz Koeppl

Tamed Langevin sampling under weaker conditions

Iosif Lytras, Panayotis Mertikopoulos

Collaborative non-parametric two-sample testing

Alejandro David De la Concha Duarte, Nicolas Vayatis, Argyris Kalogeratos

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

Hung-Hsu Chou, Johannes Maly, Claudio Mayrink Verdun, Bernardo Freitas Paulo da Costa, Heudson Mirandola

Consistent Validation for Predictive Methods in Spatial Settings

David R. Burt, Yunyi Shen, Tamara Broderick

Cubic regularized subspace Newton for non-convex optimization

Jim Zhao, Nikita Doikov, Aurelien Lucchi

On Tradeoffs in Learning-Augmented Algorithms

Ziyad Benomar, Vianney Perchet

Ordered V-information Growth: A Fresh Perspective on Shared Information

Rohan Ghosh, Mehul Motani

Safe exploration in reproducing kernel Hilbert spaces

Abdullah Tokmak, Kiran G. Krishnan, Thomas B. Schön, Dominik Baumann

Score matching for bridges without learning time-reversals

Elizabeth Louise Baker, Moritz Schauer, Stefan Sommer

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

Raphaël Carpintero Perez, Sébastien Da Veiga, Josselin Garnier, Brian Staber

Stein Boltzmann Sampling: A Variational Approach for Global Optimization

Gaëtan Serré, Argyris Kalogeratos, Nicolas Vayatis

Optimal estimation of linear non-Gaussian structure equation models

Sunmin Oh, Seungsu Han, Gunwoong Park