Skip to content
conftrace_

AISTATS 2026

588 papers

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

Max Qiushi Lin, Reza Asad, Kevin Tan, Haque Ishfaq, Csaba Szepesvári

Towards Sensitivity-Aware Language Models

Dren Fazlija, Iyiola Emmanuel Olatunji, Daniel Kudenko, Sandipan Sikdar

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

Adrien Fradin, Abdurakhmon Sadiev, Laurent Condat, Peter Richtarik

Certifying Reading Comprehension in Large Language Models

Isha Chaudhary, Vedaant V Jain, Gagandeep Singh

Generalized Correlation Shifting for Lasso

Izuru Miyazaki, Hironori Fujisawa

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

Jiayu Qin, Zhengquan Luo, Jian Chen, Xuhui Li, Jiayi Chen

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

Jaihoon Kim, Rajarshi Saha, Youngsuk Park, Minhyuk Sung

Gradient-Flow SDEs Have Unique Transient Population Dynamics

Vincent Guan, Joseph Janssen, Nicolas Lanzetti, Antonio Terpin, Geoffrey Schiebinger

On the Optimal Regret of Collaborative Personalized Linear Bandits

Bruce Huang, Ruida Zhou, Lin F. Yang, Suhas Diggavi

Conservative Inference in Switchback Experiments

Jose Blanchet, Peter Glynn, Ramesh Johari, Linjia Wu, Wenqian Xing

Where the Score Lives: A Wavelet View of Diffusion

Emma Lucia Byrnes Finn, Binxu Wang, T. Anderson Keller, Demba E. Ba

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

António Góis, Sophia Günlük, Nir Rosenfeld, Nidhi Hegde, Simon Lacoste-Julien

Provable Accelerated Bayesian Optimization with Knowledge Transfer

Haitao Lin, Boxin Zhao, Mladen Kolar, Chong Liu

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification

Ziyi Wang, Siva Rajesh Kasa, Ankith M S, SANTHOSH KUMAR KASA, Jiaru Zou

On the Role of Depth in the Expressivity of RNNs

Maude Lizaire, Michael Rizvi-Martel, Éric Dupuis, Guillaume Rabusseau

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

Jonathan Patsenker, Henry Li, Myeongseob Ko, Ruoxi Jia, Yuval Kluger

Moonwalk: Inverse-Forward Differentiation

Dmitrii Krylov, Armin Karamzade, Roy Fox

Undersmoothing Black-Box Models for Functional Estimation

Yue Yu, Debarghya Mukherjee, Moulinath Banerjee, Yaacov Ritov

On the Misinformation in a Statistical Experiment

Jake Callahan, Tommie Catanach

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

Antony Sikorski, Michael Ivanitskiy, Nathan Lenssen, Douglas Nychka, Daniel Mckenzie

Hellinger Multimodal Variational Autoencoders

Huyen Thuc Khanh Vo, Isabel Valera

Boosted GFlowNets: Improving Exploration via Sequential Learning

Pedro Dall’Antonia, Tiago Silva, Daniel Augusto de Souza, César Lincoln Mattos, Diego Mesquita

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

Leo Benac, Abhishek Sharma, Sonali Parbhoo, Finale Doshi-velez

Recency Biased Causal Attention for Time-series Forecasting

Kareem Hegazy, Michael W. Mahoney, N. Benjamin Erichson

Evaluation of Large Language Models via Coupled Token Generation

Nina L. Corvelo Benz, Stratis Tsirtsis, Eleni Straitouri, Ivi Chatzi, Ander Artola Velasco

Unified Causal Discovery and Missing Data Imputation

Osman Mian, Jens Kleesiek, Michael Kamp

Time Series Forecasting with Hahn Kolmogorov-Arnold Networks

Md Zahidul Hasan, Abdessamad Ben Hamza, Nizar Bouguila

Time-Aware Synthetic Control

Saeyoung Rho, Cyrus Illick, Samhitha Narasipura, Alberto Abadie, Daniel Hsu

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

Lejs Deen Behric, Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil

Learning Hyperparameters via a Data-Emphasized Variational Objective

Ethan Harvey, Mikhail Petrov, Michael C Hughes

Why Is Prompting Hard? Understanding Prompts on Binary Sequence Predictors

Li Kevin Wenliang, Anian Ruoss, Jordi Grau-moya, Marcus Hutter, Tim Genewein

Information-Theoretic Error Bounds for Source Localization in Neural Sensing

Leighton Pate Barnes, Yuxin Guo, Alex Dytso, Pulkit Grover

Best Policy Learning From Trajectory Preference Feedback

Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Zheng Wen

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

Zachary Bastiani, Mike Kirby, Jacob Hochhalter, Shandian Zhe

Active Subspaces in Infinite Dimension

Poorbita Kundu, Nathan Wycoff

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

Christopher Ratigan, Kyle Heuton, Carissa Wang, Lenore Cowen, Michael C Hughes

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

Sunmook Choi, Yahya Sattar, Yassir Jedra, Maryam Fazel, Sarah Dean

Efficient and Accurate Tensor Compression via Recursive Sketching

Amit Sharma, Mohammad Azhar Khan, Rameshwar Pratap

Efficient Logistic Regression with Mixture of Sigmoids

Federico Di Gennaro, Saptarshi Chakraborty, Nikita Zhivotovskiy

Conditional Flow Matching for Bayesian Posterior Inference

Percy S. Zhai, Sowon Jeong, Veronika Ročková

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

Shanyun Gao, Raghavendra Addanki, Tong Yu, Ryan A. Rossi, Qifan Song

PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures

Hind Atbir, Farah Cherfaoui, Guillaume Metzler, Emilie Morvant, Paul Viallard

Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning

Diksha Gupta, Antonio Honsell, CHUAN XU, Nirupam Gupta, Giovanni Neglia

Differentially Private E-Values

Daniel Csillag, Diego Mesquita

Local Causal Discovery for Statistically Efficient Causal Inference

Mátyás Schubert, Tom Claassen, Sara Magliacane

Efficient Swap Regret Minimization in Combinatorial Bandits

Andreas Kontogiannis, Vasilis Pollatos, Panayotis Mertikopoulos, Ioannis Panageas

Thompson Sampling-like Algorithms for Stochastic Rising Bandits

Marco Fiandri, Alberto Maria Metelli, Francesco Trovò

Variational Inference via Radial Transport

Luca Ghafourpour, Sinho Chewi, Alessio Figalli, Aram-Alexandre Pooladian

A Bayesian Information-Theoretic Approach to Data Attribution

Dharmesh Tailor, Nicolò Felicioni, Kamil Ciosek

Minimax-Optimal Two-Sample Test with Sliced Wasserstein

Binh Thuan Tran, Nicolas Schreuder

AlphaFold’s Bayesian Roots in Probability Kinematics

Thomas Hamelryck, Kanti V. Mardia

Reinforcement Learning Using Known Invariances

Alexandru Cioba, Aya Kayal, Laura Toni, Sattar Vakili, Alberto Bernacchia

FastRank: Fast Tensor Rank Approximation based on Spectral Energy

Konstantinos Bougiatiotis, Georgios Paliouras

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

Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic

On the Calibration of Survival Models with Competing Risks

Julie Alberge, Tristan Haugomat, Gael Varoquaux, Judith Abécassis

Asymptotic Optimality Theory of Confidence Intervals of the Mean

Vikas Deep, Achal Bassamboo, Sandeep Kumar Juneja

Sharp Risk Bounds for Early-stopping in Gaussian Linear Regression

Tobias Wegel, Gil Kur, Patrick Rebeschini

Robust Estimation of Heterogeneous Treatment Effects in Randomized Trials Leveraging External Data

Rickard K.A. Karlsson, Piersilvio De Bartolomeis, Issa Dahabreh, Jesse H. Krijthe

Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance

Leoni Carla Wirth, Gholamali Aminian, Gesine Reinert

Sparse Offline Reinforcement Learning with Corruption Robustness

Nam Phuong Tran, Andi Nika, Goran Radanovic, Long Tran-Thanh, Debmalya Mandal

The Majority Vote Paradigm Shift: When Popular Meets Optimal

Antonio Purificato, Maria Sofia Bucarelli, Anil Kumar Nelakanti, Andrea Bacciu, Fabrizio Silvestri

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

Batuhan K. Karaman, Aditya Rawal, Mohammad Ghavamzadeh, Suhaila Shakiah, Arijit Biswas

Rethinking Probabilistic Circuit Parameter Learning

Anji Liu, Zilei Shao, Guy Van den Broeck