| 2026 | COLT | Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum. | Nived Rajaraman, Audrey Huang, Miro Dudk, Robert E. Schapire, Dylan J. Foster, Akshay Krishnamurthy |
| 2025 | COLT | Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration. | Dylan J. Foster, Zakaria Mhammedi, Dhruv Rohatgi |
| 2025 | COLT | Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract). | Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster |
| 2025 | COLT | Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning. | Dhruv Rohatgi, Dylan J. Foster |
| 2025 | ICLR | Self-Improvement in Language Models: The Sharpening Mechanism. | Audrey Huang, Adam Block, Dylan J. Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy |
| 2025 | ICLR | Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization. | Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan J. Foster |
| 2025 | ICLR | Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF. | Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Hassan Awadallah, Alexander Rakhlin |
| 2025 | ICML | Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment. | Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan J. Foster |
| 2024 | ICLR | Harnessing Density Ratios for Online Reinforcement Learning. | Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie |
| 2024 | ICLR | Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression. | Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang |
| 2024 | ICML | Rich-Observation Reinforcement Learning with Continuous Latent Dynamics. | Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy |
| 2024 | ICML | Scalable Online Exploration via Coverability. | Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy |
| 2023 | COLT | On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring. | Dean P. Foster, Dylan J. Foster, Noah Golowich, Alexander Rakhlin |
| 2023 | COLT | Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient. | Dylan J. Foster, Noah Golowich, Yanjun Han |
| 2023 | COLT | Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression. | Aleksandrs Slivkins, Karthik Abinav Sankararaman, Dylan J. Foster |
| 2023 | COLT | Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory. | Andrew J. Wagenmaker, Dylan J. Foster |
| 2023 | ICLR | The Role of Coverage in Online Reinforcement Learning. | Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade |
| 2023 | ICML | Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games. | Dylan J. Foster, Noah Golowich, Sham M. Kakade |
| 2023 | ICML | Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL. | Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin |
| 2022 | COLT | Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information. | Yonathan Efroni, Dylan J. Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford |
| 2022 | COLT | Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation. | Dylan J. Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu |
| 2022 | ICML | Contextual Bandits with Large Action Spaces: Made Practical. | Yinglun Zhu, Dylan J. Foster, John Langford, Paul Mineiro |
| 2021 | COLT | Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective. | Dylan J. Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu |
| 2020 | COLT | Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations. | Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan |
| 2020 | COLT | Open Problem: Model Selection for Contextual Bandits. | Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo |
| 2020 | ICML | Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance. | Blair L. Bilodeau, Dylan J. Foster, Daniel M. Roy |
| 2020 | ICML | Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles. | Dylan J. Foster, Alexander Rakhlin |
| 2020 | ICML | Logarithmic Regret for Adversarial Online Control. | Dylan J. Foster, Max Simchowitz |
| 2020 | ICML | Naive Exploration is Optimal for Online LQR. | Max Simchowitz, Dylan J. Foster |
| 2020 | IJCAI | Statistical Learning with a Nuisance Component (Extended Abstract). | Dylan J. Foster, Vasilis Syrgkanis |
| 2019 | COLT | Sum-of-squares meets square loss: Fast rates for agnostic tensor completion. | Dylan J. Foster, Andrej Risteski |
| 2019 | COLT | Statistical Learning with a Nuisance Component. | Dylan J. Foster, Vasilis Syrgkanis |
| 2019 | COLT | The Complexity of Making the Gradient Small in Stochastic Convex Optimization. | Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake E. Woodworth |
| 2019 | ICML | Distributed Learning with Sublinear Communication. | Jayadev Acharya, Chris De Sa, Dylan J. Foster, Karthik Sridharan |
| 2018 | AISTATS | Inference in Sparse Graphs with Pairwise Measurements and Side Information. | Dylan J. Foster, Karthik Sridharan, Daniel Reichman |
| 2018 | COLT | Logistic Regression: The Importance of Being Improper. | Dylan J. Foster, Satyen Kale, Haipeng Luo, Mehryar Mohri, Karthik Sridharan |
| 2018 | COLT | Online Learning: Sufficient Statistics and the Burkholder Method. | Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan |
| 2018 | ICML | Practical Contextual Bandits with Regression Oracles. | Dylan J. Foster, Alekh Agarwal, Miroslav Dudk, Haipeng Luo, Robert E. Schapire |
| 2017 | COLT | ZigZag: A New Approach to Adaptive Online Learning. | Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan |