activity
20092024
most citedTheory of Deep Learning IIb: Optimization Properties of SGD

44 citations · 159 across the 33 of their papers we have counts for

collaborators
Showing 2024Show all

5 papers · 1 filter

cs.LG2024★ 1 cited

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy +3

Reinforcement learning from human feedback (RLHF) has emerged as a central tool for language model alignment. We consider online exploration in RLHF, which exploits interactive acc…

cs.LG2024

The Power of Resets in Online Reinforcement Learning

Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin

Simulators are a pervasive tool in reinforcement learning, but most existing algorithms cannot efficiently exploit simulator access -- particularly in high-dimensional domains that…

stat.ML2024

Online Estimation via Offline Estimation: An Information-Theoretic Framework

Dylan J. Foster, Yanjun Han, Jian Qian +1

The classical theory of statistical estimation aims to estimate a parameter of interest under data generated from a fixed design ("offline estimation"), while the contemporary t…

cs.LG2024

Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data

Zeyu Jia, Alexander Rakhlin, Ayush Sekhari +1

We revisit the problem of offline reinforcement learning with value function realizability but without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et al.…

stat.ML2024

On the Performance of Empirical Risk Minimization with Smoothed Data

Adam Block, Alexander Rakhlin, Abhishek Shetty

In order to circumvent statistical and computational hardness results in sequential decision-making, recent work has considered smoothed online learning, where the distribution of…