Dylan J. Foster

21 papers · 2017–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+6 more ↓

🗺️ Taxonomy Completionist (34) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

🔬 Deep Specialist (11) 🏆 Keyword Champion (4) ⚡ Prolific Year · Productive ❓ The Questioner (2) 🗃️ Keyword Collector (102) 💎 Century Club · Bronze

Venues

COLT (13) NeurIPS (6) IJCAI (1) JMLR (1)

Top co-authors

Alexander Rakhlin (6) Dylan J Foster (6) Karthik Sridharan (5) Akshay Krishnamurthy (4) Yanjun Han (3) Ayush Sekhari (2) Haipeng Luo (2) Zakaria Mhammedi (2) Jian Qian (2) Adam Block (2)

Research topics

Machine Learning (19) Optimization & Theory (16) Mathematics & Optimization (10) Optimization (8) Artificial Intelligence (7) Learning Types (7) Core AI (5) Reinforcement Learning (4) Core Methods (4) Mathematics (3) Methods (3) Application Areas (2) Learning Paradigms (2) Applications (1)

Keywords

regret bound (6) sample complexity (5) online learning (5) reinforcement learning (4) interactive decision making (4) function approximation (3) statistical learning (3) learning theory (3) neyman orthogonality (2) sample-efficient learning (2) decision-estimation coefficient (2) domain adaptation (2) contextual bandit (2) information theory (2) stationary point (2) oracle complexity (2) multi-armed bandit (2) excess risk (2) lower bound (2) in-context learning (1)

Papers

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract) COLT 2025 Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning COLT 2025 Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability NeurIPS 2024 Can large language models explore in-context? NeurIPS 2024 Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression JMLR 2024 Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning NeurIPS 2024 Online Estimation via Offline Estimation: An Information-Theoretic Framework NeurIPS 2024 Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity NeurIPS 2024 The Power of Resets in Online Reinforcement Learning NeurIPS 2024 Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory COLT 2023 On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring COLT 2023 Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient COLT 2023 Open Problem: Model Selection for Contextual Bandits COLT 2020 Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations COLT 2020 Statistical Learning with a Nuisance Component (Extended Abstract) IJCAI 2020 Statistical Learning with a Nuisance Component COLT 2019 Sum-of-squares meets square loss: Fast rates for agnostic tensor completion COLT 2019 The Complexity of Making the Gradient Small in Stochastic Convex Optimization COLT 2019 Logistic Regression: The Importance of Being Improper COLT 2018 Online Learning: Sufficient Statistics and the Burkholder Method COLT 2018 ZigZag: A New Approach to Adaptive Online Learning COLT 2017