activity
20172023
most citedFine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

256 citations · 627 across the 30 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.GT20222 cited

Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games

Shicong Cen, Yuejie Chi, Simon S. Du +1

Multi-Agent Reinforcement Learning (MARL) -- where multiple agents learn to interact in a shared dynamic environment -- permeates across a wide range of critical applications. Whil…

cs.LG20221 cited

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path

Haoyuan Cai, Tengyu Ma, Simon Du

We revisit the incremental autonomous exploration problem proposed by Lim & Auer (2012). In this setting, the agent aims to learn a set of near-optimal goal-conditioned policies to…

cs.LG2022

Nearly Minimax Algorithms for Linear Bandits with Shared Representation

Jiaqi Yang, Qi Lei, Jason D. Lee +1

We give novel algorithms for multi-task and lifelong linear bandits with shared representation. Specifically, we consider the setting where we play linear bandits with dimensio…

cs.AI20222 cited

TransFollower: Long-Sequence Car-Following Trajectory Prediction through Transformer

Meixin Zhu, Simon S. Du, Xuesong Wang +4

Car-following refers to a control process in which the following vehicle (FV) tries to keep a safe distance between itself and the lead vehicle (LV) by adjusting its acceleration i…

cs.LG20221 cited

Active Multi-Task Representation Learning

Yifang Chen, Simon S. Du, Kevin Jamieson

To leverage the power of big data from source tasks and overcome the scarcity of the target task samples, representation learning based on multi-task pretraining has become a stand…