ALT 2025 will be held over 4 days (Mon-Thu) with ShaiFest on the following day (Fri). Each accepted paper will be presented as a 10-minute talk, with 2 minutes for questions. There will also be a poster session each day.
See below the table for the talks in each section.
This is the end of the main ALT 2026 Conference. ShaiFest will follow on Friday, February 27. See the ShaiFest page for more information and a schedule
Talk Schedule
Session 1: Monday 9:30 – 10:30
Regularized Robustly Reliable Learners Avrim Blum, Donya Saless
Learning with Monotone Adversarial Corruptions Kasper Green Larsen, Chirag Pabbaraju, Abhishek Shetty
Group-realizable multi-group learning by minimizing empirical risk Navid Ardeshir, Samuel Deng, Daniel Hsu, Jingwen Liu
Improved Replicable Boosting with Majority-of-Majorities Kasper Green Larsen, Markus Engelund Mathiasen, Clement Svendsen
Sample-Near-Optimal Agnostic Boosting in Fixed-Parameter Tractable Time Arthur da Cunha, Mikael Møller Høgsgaard, Andrea Paudice
Session 2: Monday 2:00 – 3:00
Sink equilibria and the attractors of learning in games Oliver Biggar, Christos H. Papadimitriou
Last-iterate Convergence for Symmetric, General-sum, 2 × 2 Games Under The Exponential Weights Dynamic Guanghui Wang, Krishna Acharya, Lokranjan Lakshmikanthan, Vidya Muthukumar, Juba Ziani
A Novel Data-Dependent Learning Paradigm for Large Hypothesis Classes Alireza F. Pour, Shai Ben-David
Learning from Synthetic Data: Limitations of ERM Kareem Amin, Alex Bie, Weiwei Kong, Umar Syed, Sergei Vassilvitskii
Session 3: Monday 3:30 – 4:45
Closeness testing from distributed measurements Clement Louis Canonne, Aditya Vikram Singh
Nearly Minimax Discrete Distribution Estimation in Kullback-Leibler Divergence with High Probability Dirk van der Hoeven, Julia Olkhovskaya, Tim van Erven
On Purely Private Covariance Estimation Tommaso d’Orsi, Gleb Novikov
Differentially Private Bilevel Optimization Guy Kornowski
Privately Learning Decision Lists and a Differentially Private Winnow Mark Bun, William Fang
Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy Ruihan Wu, Yu-Xiang Wang
Session 4: Tuesday 9:00 – 10:30
Phase Transition of Regret for Logistic Regression with Large Weights Michael Drmota, Philippe Jacquet, Changlong Wu, Wojciech Szpankowski
Optimal L2 Regularization in High-dimensional Continual Linear Regression Gilad Karpel, Edward Moroshko, Ran Levinstein, Ron Meir, Daniel Soudry, Itay Evron
Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential Yuping Zheng, Andrew Lamperski
Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method Jiaming Liang
Accelerated Mirror Descent for Non-Euclidean Star-convex Functions Clement LEZANE, Sophie Langer, Wouter M Koolen
DS-Compatible Log-Linear Reliability with KL-Prox EM: Monotone Ascent, Identifiability, and Generalization Shiva Koreddi, Sravani Sowrupilli
Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications Zijian Liu
Session 5: Tuesday 2:00 – 3:00
Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model Xingtu Liu, Lin F. Yang, Sharan Vaswani
Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization Matan Schliserman, Tomer Koren
Smoothed Online Optimization for Target Tracking: Robust and Learning-Augmented Algorithms Ali Zeynali, Mahsa Sahebdel, Qingsong Liu, Ramesh K. Sitaraman, Mohammad Hajiesmaili
Sparse Nonparametric Contextual Bandits Hamish Flynn, Julia Olkhovskaya, Paul Rognon-Vael
Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds Oscar Villemaud, Suryanarayana Sankagiri, Matthias Grossglauser
Session 6: Tuesday 3:30 – 4:45
On the Hardness of Learning Regular Expressions Idan Attias, Lev Reyzin, Nathan Srebro, Gal Vardi
Large Average Subtensor Problem: Ground-State, Algorithms, and Algorithmic Barriers Abhishek Hegade K. R., Eren C. Kizildag
The Planted Number Partitioning Problem Eren C. Kizildag
Uniform Convergence Beyond Glivenko-Cantelli Tanmay Devale, Pramith Devulapalli, Steve Hanneke
Optimal Bounds for Tyler’s M-Estimator for Elliptical Distributions Akshay Ramachandran, Lap Lau
Talagrand Meets Talagrand: Upper and Lower Bounds on Expected Soft Maxima of Gaussian Processes with Finite Index Sets Yifeng Chu, Maxim Raginsky
Session 7: Wednesday 9:00 – 10:30
Distribution-Dependent Rates for Multi-Distribution Learning Rafael Hanashiro, Patrick Jaillet
From Continual Learning to SGD and Back: Better Rates for Continual Linear Models Itay Evron, Ran Levinstein, Matan Schliserman, Uri Sherman, Tomer Koren, Daniel Soudry, Nathan Srebro
Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift Robi Bhattacharjee, Nicholas Rittler, Kamalika Chaudhuri
Efficient and Provable Algorithms for Covariate Shift Deeksha Adil, Jaroslaw Blasiok
Multi-distribution Learning: From Worst-Case Optimality to Lexicographic Min-Max Optimality Guanghui Wang, Umar Syed, Robert E. Schapire, Jacob Abernethy
PAC-Bayesian Analysis of the Surrogate Relation between Joint Embedding and Supervised Downstream Losses Theresa Wasserer, Maximilian Fleissner, Debarghya Ghoshdastidar
Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure Zhi Wang, Chicheng Zhang, Ramya Korlakai Vinayak
On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning Haoyuan Sun, Ali Jadbabaie, Navid Azizan
Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Learnable Channel Attention Yingzhen Yang
Online Markov Decision Processes with Terminal Law Constraints Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane
Online and Offline Learning of Orderly Hypergraphs Using Queries Shaun Fallat, Kamyar Khodamoradi, David G. Kirkpatrick, Valerii Maliuk, Seyed Ahmad Mojallal, Sandra Zilles
Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm Pierre Boudart, Pierre Gaillard, Alessandro Rudi
Session 10: Thursday 9:00 – 10:30
Graph Inference with Effective Resistance Queries Evelyn Warton, Huck Bennett, Mitchell Black, Amir Nayyeri
Compressibility Barriers to Neighborhood-Preserving Data Visualization Szymon Snoeck, Noah Bergam, Nakul Verma
Predictive inference for time series: why is split conformal effective despite temporal dependence? Rina Foygel Barber, Ashwin Pananjady
Universality of conformal prediction under the assumption of randomness Vladimir Vovk
A Martingale Kernel Two-Sample Test Anirban Chatterjee, Aaditya Ramdas