[edit]

Volume 336: The Thirty Ninth Annual Conference on Learning Theory, 29-3 July 2026, San Diego, California

[edit]

Editors: Steve Hanneke, Tor Lattimore

[bib][citeproc]

Contents:

Preface

Conference on Learning Theory 2026: Preface

Steve Hanneke, Tor Lattimore; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:i-i

Original Papers

How fast can you find a good hypothesis?

Anders Aamand, Maryam Aliakbarpour, Justin Y. Chen, Sandeep Silwal; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1-2

On efficient robust regression with subquadratic samples

Deeksha Adil, Jarosław Błasiok, Hongjie Chen, Deepak Narayanan Sridharan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3-74

Quiet Planting for $k$-SAT, Multiple Solutions of Arbitrary Geometry

Ali Ahmadi, Kiarash Banihashem, Iman Gholami, Mohammad Taghi Hajiaghayi, Jan Olkowski; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:75-105

Optimal Prediction-Augmented Algorithms for Testing Independence of Distributions

Maryam Aliakbarpour, Alireza Azizi, Ria Stevens; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:106-157

Query Efficient Structured Matrix Learning

Noah Amsel, Pratyush Avi, Tyler Chen, Feyza Duman Keles, Chinmay Hegde, Christopher Musco, Cameron Musco, David Persson; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:158-194

Swap Regret Minimization Through Response-Based Approachability

Ioannis Anagnostides, Gabriele Farina, Maxwell Fishelson, Haipeng Luo, Jon Schneider; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:195-223

Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures

Prashanti Anderson, Mitali Bafna, Rares-Darius Buhai, Pravesh K. Kothari, David Steurer; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:224-289

Statistical Learning from Attribution Sets

Lorne Applebaum, Robert Busa-Fekete, August Chen, Claudio Gentile, Tomer Koren, Aryan Mokhtari; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:290-336

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization

Aleksandar Armacki, Dragana Bajović, Dušan Jakovetić, Soummya Kar, Ali H Sayed; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:337-370

Learning depth-3 circuits via quantum agnostic boosting

Srinivasan Arunachalam, Arkopal Dutt, Alexandru Gheorghiu, Michael De Oliveira; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:371-426

Strongly Polynomial Time Complexity of Policy Iteration for $L_∞$ Robust MDPs

Ali Asadi, Krishnendu Chatterjee, Ehsan Goharshady, Mehrdad Karrabi, Alipasha Montaseri, Carlo Pagano; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:427-457

Margin in Abstract Spaces

Yair Ashlagi, Roi Livni, Shay Moran, Tom Waknine; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:458-471

A Complexity Measure for Active Learning in Multi-group Mean Estimation

Abdellah Aznag, Rachel Cummings, Adam N. Elmachtoub; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:472-473

Variational Tail Bounds for Norms of Random Vectors and Matrices

Sohail Bahmani; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:474-504

Cloning is as Hard as Learning for Stabilizer States

Nikhil Bansal, Matthias C. Caro, Gaurav Mahajan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:505-558

Limitations of SGD for Multi-Index Models Beyond Statistical Queries

Daniel Barzilai, Ohad Shamir; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:559-612

Algorithmic Thinking Theory

MohammadHossein Bateni, Vincent Cohen-Addad, Yuzhou Gu, Silvio Lattanzi, Simon Meierhans, Christopher Mohri; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:613-639

Omniprediction with Long-Term Constraints

Yahav Bechavod, Jiuyao Lu, Aaron Roth; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:640-683

Adaptive Weighted Averaging

Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:684-707

Actively Learning Halfspaces without Synthetic Data

Hadley Black, Kasper Green Larsen, Arya Mazumdar, Barna Saha, Geelon So; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:708-728

Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness

Moïse Blanchard, Abhishek Shetty, Alexander Rakhlin; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:729-759

Partition Function Estimation under Bounded $f$-Divergence

Adam Block, Abhishek Shetty; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:760-790

Tight list replicability bounds via a novel sphere covering theorem

Ari Blondal, Hamed Hatami, Pooya Hatami, Chavdar Lalov, Sivan Tretiak; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:791-807

Learning from Equivalence Queries, Revisited

Mark Braverman, Roi Livni, Yishay Mansour, Shay Moran, Kobbi Nissim; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:808-836

Learning Conditional Averages

Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:837-858

Active Learning on Adversarially Corrupted Graphs

Marco Bressan, Nicolò Cesa-Bianchi, Tommaso d’Orsi, Emmanuel Esposito, Silvio Lattanzi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:859-895

Universal priors: solving empirical Bayes via Bayesian inference and pretraining

Nick Cannella, Anzo Teh, Yanjun Han, Yury Polyanskiy; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:896-937

Phase Transition for Stochastic Block Model with more than $\sqrtn$ Communities

Alexandra Carpentier, Christophe Giraud, Nicolas Verzelen; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:938-1000

Learning Periodic Strategies in Blocking Bandits Is as Hard as Bandits with Switching Costs

Nicolò Cesa-Bianchi, Junya Honda, Yuko Kuroki, Atsushi Miyauchi, Lukas Zierahn; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1001-1021

A Characterization of List Language Identification in the Limit

Moses Charikar, Chirag Pabbaraju, Ambuj Tewari; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1022-1053

Language Identification with Succinct Machine-Independent Traces

Moses Charikar, Jon Kleinberg, Chirag Pabbaraju; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1054-1074

A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice

Zachary Chase, Shinji Ito, Idan Mehalel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1075-1087

Faster Newton Methods for Convex and Nonconvex Optimization in Gradient Complexity

Lesi Chen, Chengchang Liu, Luo Luo, Jingzhao Zhang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1088-1112

Separating Oblivious and Adaptive Models of Variable Selection (Extended Abstract)

Ziyun Chen, Jerry Li, Kevin Tian, Yusong Zhu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1113-1114

Instance-optimal high-precision shadow tomography with few-copy measurements: A metrological approach

Senrui Chen, Weiyuan Gong, Sisi Zhou; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1115-1185

Information-computation gaps in quantum learning via low-degree likelihood

Sitan Chen, Weiyuan Gong, Jonas Haferkamp, Yihui Quek; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1186-1278

Optimal Inference Schedules for Masked Diffusion Models

Sitan Chen, Kevin Cong, Jerry Li; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1279-1311

Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression

Fan Chen, Jian Qian, Alexander Rakhlin, Nikita Zhivotovskiy; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1312-1340

High-Accuracy Log-Concave Sampling with Stochastic Queries

Fan Chen, Sinho Chewi, Constantinos Daskalakis, Alexander Rakhlin; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1341-1372

Calibeating Made Simple

Yurong Chen, Zhiyi Huang, Michael I. Jordan, Haipeng Luo; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1373-1398

Is Memorization Helpful or Harmful? Prior Information Sets the Threshold

Chen Cheng, Rina Foygel Barber; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1399-1433

DDPM Score Matching and Distribution Learning (Extended Abstract)

Sinho Chewi, Alkis Kalavasis, Anay Mehrotra, Omar Montasser; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1434-1435

Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more

Spencer Compton, Jerry Li; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1436-1475

Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data

Collin Cranston, Zhichao Wang, Todd Kemp, W. Michael Mahoney; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1476-1574

Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension

Michael Crawshaw, Mingrui Liu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1575-1610

Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method

Yatin Dandi, David Gamarnik, Francisco Pernice, Lenka Zdeborová; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1611-1646

Estimating Ising Models in Total Variation Distance

Constantinos Daskalakis, Vardis Kandiros, Rui Yao; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1647-1714

Stochastic Safe Action Model Learning

Zihao Deng, Brendan Juba; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1715-1736

The matrix-vector complexity of Ax=b

Michał Dereziński, Ethan N Epperly, Raphael A Meyer; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1737-1770

Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size

Michał Dereziński, Xiaoyu Dong; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1771-1813

High-Dimensional Gaussian Mean Estimation under Realizable Contamination

Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1814-1856

Linear Regression under Missing or Corrupted Coordinates

Ilias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane, Jasper C. H. Lee, Thanasis Pittas; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1857-1901

A Quasi-Polynomial Time Mean Estimator Under Mean-Shift Contamination with Unknown Covariance

Ilias Diakonikolas, Jingyi Gao, Giannis Iakovidis, Daniel M. Kane, Sihan Liu, Thanasis Pittas; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1902-1937

Online Convex Optimization with Sublinear Noisy Probes

Simone Di Gregorio, Anupam Gupta, Stefano Leonardi, Matteo Russo; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1938-1962

Minimax optimal differentially private synthetic data for smooth queries

Rundong Ding, Yiyun He, Yizhe Zhu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1963-1964

Rate-optimal community detection near the KS threshold via node-robust algorithms

Jingqiu Ding, Yiding Hua, Kasper Lindberg, David Steurer, Aleksandr Storozhenko; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:1965-2037

Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees

Daniil Dmitriev, Zhihan Huang, Yuting Wei; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2038-2104

Online Realizable Regression and Applications for ReLU Networks

Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2105-2106

Relatively Smart: A New Approach for Instance-Optimal Learning

Shaddin Dughmi, Alireza F. Pour; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2107-2144

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network

Abhigyan Dutta, Itay Safran, Paul Valiant; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2145-2199

Theoretical Compression Bounds for Wide Multilayer Perceptrons

Houssam El Cheairi, David Gamarnik, Rahul Mazumder; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2200-2258

Leveraging Similarities in Multi-Armed Bandits

Khaled Eldowa, Thibaud Rahier, Augustin Cablant, Panayotis Mertikopoulos, Pierre Gaillard; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2259-2306

The Sample Complexity of Multiclass and Sparse Contextual Bandits

Liad Erez, Fan Chen, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran, Alexander Rakhlin; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2307-2338

Tight Sample Complexity Bounds for Entropic Best Policy Identification

Amer Essakine, Claire Vernade; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2339-2398

Defensive Generation

Gabriele Farina, Juan Carlos Perdomo; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2399-2427

Optimal Reconstruction from Linear Queries

Yuval Filmus, Shay Moran, Elizaveta Nesterova; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2428-2476

Space-Efficient Language Generation in the Limit

Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov, Miltiadis Stouras, Ola Svensson; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2477-2502

Toward Simultaneously Optimal Regret in U-Calibration

Rafael Frongillo, Haipeng Luo, Nishant A. Mehta, Jon Schneider; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2503-2534

Learning Ising Models from Evolutions (Extended Abstract)

Jason Gaitonde, Ankur Moitra, Elchanan Mossel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2535-2536

Optimal Hardness of Online Algorithms for Large Common Induced Subgraphs

David Gamarnik, Miklós Z. Rácz, Gabe Schoenbach; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2537-2560

Fast and Large-Scale Unbalanced Optimal Transport via its Semi-Dual and Adaptive Gradient Methods

Ferdinand Genans; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2561-2600

Nearly Linear-Time User-Level DP-SCO with Optimal Rates

Badih Ghazi, Ravi Kumar, Daogao Liu, Pasin Manurangsi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2601-2636

Fixed-Parameter Tractability of Private Synthetic Data Generation

Badih Ghazi, Cristóbal Guzmán, Pritish Kamath, Alexander Knop, Ravi Kumar, Pasin Manurangsi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2637-2637

Universality of high-dimensional scaling limits of stochastic gradient descent (extended abstract)

Reza Gheissari, Aukosh Jagannath; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2638-2638

On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach

George Giapitzakis, Kimon Fountoulakis, Eshaan Nichani, Jason D. Lee; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2639-2678

Sample-Efficient Omniprediction for Proper Losses

Isaac Gibbs, Ryan J. Tibshirani; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2679-2719

Robust Algorithms for Finding Cliques in Random Intersection Graphs via Sum-of-Squares

Andreas Göbel, Janosch Ruff, Leon Schiller; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2720-2802

Information-Theoretic Thresholds for Bipartite Latent-Space Graphs Under Noisy Observations

Andreas Göbel, Marcus Pappik, Leon Schiller; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2803-2803

Testing Noise Assumptions of Learning Algorithms

Surbhi Goel, Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2804-2853

Compact Geometric Representations of Hierarchies

Prashant Gokhale, Piotr Indyk, Yuhao Liu, Sandeep Silwal, Tony Wang, Haike Xu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2854-2877

Randomization for Faster Exact Optimization of Discounted Markov Decision Processes

Andrei Graur, Aaron Sidford, Ta-Wei Tu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2878-2900

Computing Lewis weights to high precision using local relative smoothness

Sander Gribling, Aaron Sidford, Chenyi Zhang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2901-2939

A Unified Lower Bound on the Noisy Query Complexity of Boolean Functions

Yuzhou Gu, Xin Li, Yinzhan Xu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2940-2962

Functional Stochastic Localization

Anming Gu, Bobby Shi, Kevin Tian; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:2963-3004

High Probability Convergence Guarantees of Stochastic Gradient Descent Ascent in Structured Nonconvex Min-Max Games

Junsoo Ha; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3005-3075

An Empirical Bayes Perspective on Heteroskedastic Mean Estimation

Yanjun Han, Abhishek Shetty, Jacob Shkrob; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3076-3108

Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise

Rafael Hanashiro, Abhishek Shetty, Patrick Jaillet; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3109-3142

Price of metric universality in vector quantization is at most 0.11 bit

Alina Harbuzova, Or Ordentlich, Yury Polyanskiy; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3143-3183

Learning from Biased and Costly Data Sources: Minimax-optimal Data Collection under a Budget (extended abstract)

Michael O. Harding, Vikas Singh, Kirthevasan Kandasamy; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3184-3184

A Perfectly Truthful Calibration Measure

Jason Hartline, Lunjia Hu, Yifan Wu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3185-3223

Uniform Laws of Large Numbers in Product Spaces

Ron Holzman, Shay Moran, Alexander Shlimovich; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3224-3279

Recovery thresholds for hidden weighted sparse graphs (extended abstract)

Zhe Hou, Jingcheng Liu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3280-3284

Near-optimal Swap Regret Minimization for Convex Losses

Lunjia Hu, Jon Schneider, Yifan Wu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3285-3313

Efficient Swap Multicalibration of Elicitable Properties

Lunjia Hu, Haipeng Luo, Spandan Senapati, Vatsal Sharan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3314-3348

Wasserstein Policy Learning for Distributional Outcomes

Yiyan Huang, Cheuk Hang Leung, Qi Wu, Zhiheng Zhang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3349-3350

Reconstructing Riemannian Metrics From Random Geometric Graphs

Han Huang, Pakawut Jiradilok, Elchanan Mossel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3351-3440

Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion

Xunpeng Huang, Yingyu Lin, Lijing Kuang, Hanze Dong, Difan Zou, Yian Ma, Tong Zhang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3441-3487

Recovery of Planted Subgraphs

Wasim Huleihel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3488-3592

Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction

Lunjia Hu, Kevin Tian, Chutong Yang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3593-3634

On Randomized Algorithms in Online Strategic Classification

Chase Hutton, Adam Melrod, Han Shao; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3635-3665

Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret

Shinji Ito, Haipeng Luo, Arnab Maiti, Taira Tsuchiya, Yue Wu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3666-3692

On the Importance of Randomization in Discriminative Feature Feedback

Valentio Iverson, Tosca Lechner, Sivan Sabato; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3693-3715

Sharp analysis of linear ensemble sampling

David Janz, Arya Akhavan, Csaba Szepesvári; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3716-3750

Low-Degree Method Fails to Predict Robust Subspace Recovery

He Jia, Aravindan Vijayaraghavan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3751-3781

Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization

Ruichen Jiang, Zakaria Mhammedi, Mehryar Mohri, Aryan Mokhtari; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3782-3824

Avoiding exp($k^*$) Scaling for Thompson Sampling in Combinatorial Semi-Bandits: From Multiple Seeds to a Single Seed

Tianyuan Jin, Heyang Zhao, Vincent Y. F. Tan, Quanquan Gu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3825-3855

Ripple Mechanisms for Discrete and Private Statistics

Matthew Joseph, Alex Kulesza, Yuyan Wang, Alexander Yu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3856-3903

Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases (Extended Abstract)

Alkis Kalavasis, Anay Mehrotra, Felix Zhou; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3904-3905

Fast, Parallel, Query-Efficient Binary Classification

Ishani Karmarkar, Liam O’Carroll, Aaron Sidford; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3906-3949

Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning

David Kattermann, Lothar Sebastian Krapp; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3950-3969

Spectral Valleys and Sharp Failures in Greedy Determinant Maximization

Rajiv Khanna; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3970-3992

Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension

Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:3993-4021

Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift

Shyamal Patel, Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4022-4049

Overlap Analysis of the Shortest Path Problem: Local Search, Landscapes, and Franz-Parisi Potential

Frederic Koehler, Joonhyung Shin; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4050-4228

Ambiguous Online Learning

Vanessa Kosoy; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4229-4266

Clipping the Price of Adaptivity at the Tail

Itai Kreisler, Yair Carmon, Oliver Hinder; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4267-4307

A Distribution Testing Approach to Clustering Distributions

Gunjan Kumar, Yash Pote, Jonathan Scarlett; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4308-4348

On the Curse of Dimensionality in Private Sparse Covariance Estimation and PCA

Syamantak Kumar, Shourya Pandey, Purnamrita Sarkar, Kevin Tian; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4349-4400

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

Kuo-Wei Lai, Guanghui Wang, Molei Tao, Vidya Muthukumar; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4401-4477

Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader

Jongyeong Lee, Junya Honda, Shinji Ito, Chansoo Kim; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4478-4519

Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning

Harin Lee, Min-hwan Oh; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4520-4584

Blackwell Approachability and Gradient Equilibrium are Equivalent

Brian W. Lee, Nika Haghtalab, Michael I. Jordan, Ryan J. Tibshirani; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4585-4587

A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak–Ruppert Averaging

Wei-Cheng Lee, Francesco Orabona; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4588-4634

Self-Concordant Perturbations for Linear Bandits

Lucas Lévy, Jean-Lou Valeau, Arya Akhavan, Patrick Rebeschini; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4635-4673

Second-Order Bounds for $[0,1]$-Valued Regression via Betting Loss

Yinan Li, Sungjoon Yoon, Ethan Huang, Kwang-Sung Jun; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4674-4721

Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract)

Binghui Li, Zilin Wang, Fengling Chen, Shiyang Zhao, Ruiheng Zheng, Lei Wu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4722-4723

Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity

Haitong Liu, Deepak Narayanan Sridharan, David Steurer, Manuel Wiedmer; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4724-4818

Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation

Junyan Liu, Haipeng Luo, Zihan Zhang, Lillian J. Ratliff; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4819-4856

Regret Minimization with Adaptive Opponents in Repeated Games

Mingyang Liu, Asuman Ozdaglar, Tiancheng Yu, Kaiqing Zhang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4857-4858

Random Reshuffling Dominates Stochastic Gradient Descent

Zijian Liu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4859-4882

Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity

Hengrui Luo, Anna Ma, Ludovic Stephan, Yizhe Zhu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4883-4884

Polynomial-time sampling despite disorder chaos

Eric Ma, Tselil Schramm; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4885-4910

On the Power of Adaptivity for $\varepsilon$-Best Arm Identification in Linear Bandits

Arnab Maiti, Yunbei Xu, Kevin Jamieson; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4911-4968

Online Market Making and the Value of Observing the Order Book

Davide Maran, Marcello Restelli; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4969-4998

Phase Transition in Convex Relaxations for Graph Alignment

Laurent Massoulié, Sushil Mahavir Varma, Louis Vassaux, Irène Waldspurger; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:4999-5020

On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits

Leo Maynard-Zhang, Zhihan Xiong, Kevin Jamieson, Maryam Fazel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5021-5052

Language Generation with Infinite Contamination

Anay Mehrotra, Grigoris Velegkas, Xifan Yu, Felix Zhou; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5053-5112

Differentially Private Language Generation and Identification in the Limit (Extended Abstract)

Anay Mehrotra, Grigoris Velegkas, Xifan Yu, Felix Zhou; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5113-5114

On the Gradient Complexity of Private Optimization with Private Oracles

Michael Menart, Aleksandar Nikolov; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5115-5158

On the implicit regularization of Langevin dynamics with projected noise

Govind Menon, Austin Stromme, Adrien Vacher; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5159-5187

Steering diffusion models with quadratic rewards: a fine-grained analysis

Ankur Moitra, Andrej Risteski, Dhruv Rohatgi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5188-5209

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials

Rotem Mulayoff, Sebastian U. Stich; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5210-5243

Optimal Neural Network Approximation of Smooth Compositional Functions on Sets with Low Intrinsic Dimension

Thomas Nagler, Sophie Langer; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5244-5272

Graph neural networks extrapolate out-of-distribution for shortest paths

Robert R. Nerem, Samantha Chen, Sanjoy Dasgupta, Yusu Wang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5273-5331

An Exponential Lower Bound for Spectral Density Estimation on Unweighted Graphs

Pan Peng, Yuyang Wang, Joy Qiping Yang, Yichun Yang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5332-5357

How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?

Nikhil Garg, Jon Kleinberg, Kenny Peng; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5358-5376

Boosting with List-Decodable Codes

Addison Prairie, Li-Yang Tan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5377-5396

Deep Q-Learning on Hölder Spaces

Qian Qi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5397-5398

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits

Hao Qin, Chicheng Zhang; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5399-5464

Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach

Hao Qiu, Mengxiao Zhang, Nicolò Cesa-Bianchi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5465-5517

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum

Nived Rajaraman, Audrey Huang, Miro Dudik, Rob Schapire, Dylan Foster, Akshay Krishnamurthy; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5518-5555

Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining

Yunwei Ren, Yatin Dandi, Florent Krzakala, Jason D. Lee; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5556-5597

Continuous time policy evaluation is easier with noisy dynamics

Samuel Robertson, Thomas Newton, Csaba Szepesvári; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5598-5624

Model Agreement via Anchoring

Eric Eaton, Surbhi Goel, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5625-5661

Private Linear Regression via a Down-Sensitivity to Privacy Reduction

Ittai Rubinstein, Chris Ge, Samuel B. Hopkins; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5662-5720

A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory

Itay Safran; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5721-5742

Convergence of Continual Learning in Homogeneous Deep Networks

Matan Schliserman, Gon Buzaglo, Itay Evron, Daniel Soudry; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5743-5784

The Hidden Cost of Approximation in Online Mirror Descent

Ofir Schlisselberg, Uri Sherman, Tomer Koren, Yishay Mansour; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5785-5827

Optimal Sample Complexity Lower Bounds on Conditional Independence Testing

Jan Seyfried, Neelkanth Mishra, Sayantan Sen, Marco Tomamichel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5828-5873

Testing for a Hidden Geometry in Random Graphs

Amit Silber, Mor Oren-Loberman, Wasim Huleihel; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5874-5927

Finite Sample Bounds for Learning with Score Matching

Devin Smedira, Abhijith Jayakumar, Sidhant Misra, Marc Vuffray, Andrey Y. Lokhov; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5928-5949

Efficient Learning and Symmetry Discovery under Exact Invariances

Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet, Stefanie Jegelka; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5950-5979

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment

Ved Sriraman, Adam Block; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:5980-6028

Privately Estimating Black-Box Statistics

Günter Steinke, Thomas Steinke; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6029-6074

Truly Adapting to Adversarial Constraints in Constrained MABs

Francesco Emanuele Stradi, Kalana Kalupahana, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6075-6113

Data Augmentation: A Fourier Analysis Perspective

Behrooz Tahmasebi, Melanie Weber, Stefanie Jegelka; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6114-6155

CONVERGENCE RATES FOR DISTRIBUTION MATCHING WITH SLICED OPTIMAL TRANSPORT

Gauthier Thurin, Claire Boyer, Kimia Nadjahi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6156-6196

On the Asymptotics of Self-Supervised Pre-training: Two-Stage M-Estimation and Representation Symmetry

Mohammad Tinati, Stephen Tu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6197-6309

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6310-6371

Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^\pi$-Realizability and Concentrability

Volodymyr Tkachuk, Csaba Szepesvári, Xiaoqi Tan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6372-6405

The Monotonicity of the Franz–Parisi Potential Is Equivalent to Low-Degree MMSE Lower Bounds: Extended Abstract

Konstantinos Tsirkas, Leda Wang, Ilias Zadik; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6406-6409

Spectral Recovery of a Planted Triangle-Dense Subgraph

Sam van der Poel, Cheng Mao, Benjamin McKenna; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6410-6457

On-Average Stability of Multipass Preconditioned SGD and Effective Dimension

Simon Vary, Tyler Farghly, Ilja Kuzborskij, Patrick Rebeschini; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6458-6495

The Geometry of Efficient Nonconvex Sampling

Santosh S. Vempala, Andre Wibisono; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6496-6532

Learning with Simulators: No Regret in a Computationally Bounded World

Sasha Voitovych, Abhishek Shetty, Noah Golowich, Alexander Rakhlin; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6533-6591

Fast Score-Based Sampling via Log-Concave Reductions

Martin J. Wainwright; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6592-6621

Almost sure null bankruptcy of testing-by-betting strategies

Hongjian Wang, Shubhada Agrawal, Aaditya Ramdas; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6622-6650

A simple, optimal and efficient algorithm for online exp-concave optimization

Yi-Han Wang, Peng Zhao, Zhi-Hua Zhou; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6651-6691

Accelerated Convex Optimization via Hamiltonian Dynamics with Deterministic Integration Time

Xiuyuan Wang, Vishwak Srinivasan, Qiang Fu, Siddharth Mitra, Andre Wibisono, Ashia Wilson; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6692-6742

Diffusion-Network Alignment: An Efficient Algorithm and Explicit Probability Bounds

Ziao Wang, Lei Ying; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6743-6810

Minimax Limits of $k$-Fold Cross-Validation via Majority

Ido Nachum, Ruediger Urbanke, Thomas Weinberger; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6811-6848

Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization (Extended Abstract)

Jingfeng Wu, Peter L. Bartlett, Sham M. Kakade, Jason D. Lee, Bin Yu; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6849-6851

Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs (extended abstract)

Wu Tianhao, Matthew Zurek, Weina Wang, Qiaomin Xie; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6852-6857

Worst-case Error Bounds for Online Learning of Smooth Functions

Weian (Andrew) Xie; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6858-6884

Optimism Stabilizes Thompson Sampling for Adaptive Inference

Shunxing Yan, Han Zhong; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6885-6886

Tight Sample Complexity of Transformers

Chenxiao Yang, Nathan Srebro, Zhiyuan Li; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6887-6923

Learning Decision-Sufficient Representations for Linear Optimization

Yuhan Ye, Saurabh Amin, Asuman Özdağlar; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6924-6975

Distribution-Free Sequential Prediction with Abstentions

Jialin Yu, Moïse Blanchard; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:6976-7011

Stable algorithms Lower Bounds for Estimation from MMSE Discontinuities: Extended Abstract

Xifan Yu, Ilias Zadik; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7012-7015

Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs

Guy Zamir, Matthew Zurek, Yudong Chen; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7016-7061

Gradient-Variation Regret Bounds for Unconstrained Online Learning

Yuheng Zhao, Andrew Jacobsen, Nicolò Cesa-Bianchi, Peng Zhao; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7062-7104

Open Problems

Open Problem: How much overparametrization is needed for ALS in tensor decomposition?

Dionysis Arvanitakis, Vaidehi Srinivas, Aravindan Vijayaraghavan; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7105-7110

Invited Open Problem: Online Optimization of Piecewise-Lipschitz Functions with Applications to Data-Driven Algorithm Design

Maria-Florina Balcan, Wesley Pegden, Dravyansh Sharma; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7111-7116

Invited Open Problem: Is the Power of Deep Learning over Linear Models Inherently Distribution Dependent?

Vitaly Feldman, Pritish Kamath, Nathan Srebro; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7117-7122

Open Problem: Is Interaction Necessary for Order-Optimal 1-bit Mean Estimation?

Ivan Lau, Jonathan Scarlett; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7123-7128

Invited Open Problem: Does Differential Privacy Make PAC Learning Much Harder?

Kobbi Nissim, Uri Stemmer, Eliad Tsfadia; Proceedings of Thirty Ninth Conference on Learning Theory, PMLR 336:7129-7135

subscribe via RSS