activity
20172021
most citedFine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

256 citations · 505 across the 13 of their papers we have counts for

collaborators

21 papers

cs.LG2021

Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning

Yuanzhi Li, Ruosong Wang, Lin F. Yang

Recently there is a surge of interest in understanding the horizon-dependence of the sample complexity in reinforcement learning (RL). Notably, for an RL environment with horizon l…

cs.LG2021

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap

Yuanhao Wang, Ruosong Wang, Sham M. Kakade

A fundamental question in the theory of reinforcement learning is: suppose the optimal -function lies in the linear span of a given dimensional feature mapping, is sample-ef…

cs.LG2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL

Simon S. Du, Sham M. Kakade, Jason D. Lee +4

This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function a…

cs.LG202029 cited

Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension

Ruosong Wang, Ruslan Salakhutdinov, Lin F. Yang

Value function approximation has demonstrated phenomenal empirical success in reinforcement learning (RL). Nevertheless, despite a handful of recent progress on developing theory f…

cs.DS20202 cited

Nearly Linear Row Sampling Algorithm for Quantile Regression

Yi Li, Ruosong Wang, Lin Yang +1

We give a row sampling algorithm for the quantile loss function with sample complexity nearly linear in the dimensionality of the data, improving upon the previous best algorithm w…

cs.LG2020

Preference-based Reinforcement Learning with Finite-Time Guarantees

Yichong Xu, Ruosong Wang, Lin F. Yang +2

Preference-based Reinforcement Learning (PbRL) replaces reward values in traditional reinforcement learning by preferences to better elicit human opinion on the target objective, e…