← Authors

Dylan J Foster

39 papers · 2015–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (10) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (36) 🏠 Conference Loyalist (23) 🀝 Dynamic Duo (15) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (18) πŸ“ˆ Trend Setter ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (122) πŸ”₯ Unstoppable (11) πŸ’Ž Century Club (39) ❓ The Questioner (4)

Conferences

NIPS (23) ICLR (6) ICML (6) COLT (4)

Top co-authors

Akshay Krishnamurthy (15) Alexander Rakhlin (10) Karthik Sridharan (6) Dylan J. Foster (6) Nan Jiang (5) Zakaria Mhammedi (5) Adam Block (5) Tengyang Xie (5) Ayush Sekhari (4) John Langford (4)

Keywords

online learning (9) regret bound (8) contextual bandit (6) sample complexity (6) reinforcement learning (6) function approximation (4) multi-armed bandit (4) interactive decision making (3) learning theory (3) value function approximation (3) sample-efficient learning (2) margin bound (2) representation learning (2) online estimation (2) regression oracle (2) information theory (2) generalization bound (2) model selection (2) rademacher complexity (2) neural network (2)

Papers

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration COLT 2025
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment ICML 2025
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF ICLR 2025
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization ICLR 2025
Self-Improvement in Language Models: The Sharpening Mechanism ICLR 2025
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability NIPS 2024
The Power of Resets in Online Reinforcement Learning NIPS 2024
Online Estimation via Offline Estimation: An Information-Theoretic Framework NIPS 2024
Can large language models explore in-context? NIPS 2024
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning NIPS 2024
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity NIPS 2024
Harnessing Density Ratios for Online Reinforcement Learning ICLR 2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression ICLR 2024
Scalable Online Exploration via Coverability ICML 2024
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics ICML 2024
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient NIPS 2023
Efficient Model-Free Exploration in Low-Rank MDPs NIPS 2023
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games ICML 2023
Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression COLT 2023
The Role of Coverage in Online Reinforcement Learning ICLR 2023
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL ICML 2023
Understanding the Eluder Dimension NIPS 2022
Contextual Bandits with Large Action Spaces: Made Practical ICML 2022
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation COLT 2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information COLT 2022
Interaction-Grounded Learning with Action-Inclusive Feedback NIPS 2022
On the Complexity of Adversarial Decision Making NIPS 2022
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination NIPS 2021
Learning the Linear Quadratic Regulator from Nonlinear Observations NIPS 2020
Adapting to Misspecification in Contextual Bandits NIPS 2020
Independent Policy Gradient Methods for Competitive Reinforcement Learning NIPS 2020
Hypothesis Set Stability and Generalization NIPS 2019
Model Selection for Contextual Bandits NIPS 2019
Uniform Convergence of Gradients for Non-Convex Learning and Optimization NIPS 2018
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms NIPS 2018
Spectrally-normalized margin bounds for neural networks NIPS 2017
Parameter-Free Online Learning via Model Selection NIPS 2017
Learning in Games: Robustness of Fast Convergence NIPS 2016
Adaptive Online Learning NIPS 2015