activity
20182020
most citedRethinking the Value of Labels for Improving Class-Imbalanced Learning

212 citations · 289 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG202012 cited

Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation

Devavrat Shah, Dogyoon Song, Zhi Xu +1

We consider the question of learning -function in a sample efficient manner for reinforcement learning with continuous state and action spaces under a generative model. If -f…

cs.LG20203 cited

Stable Reinforcement Learning with Unbounded State Space

Devavrat Shah, Qiaomin Xie, Zhi Xu

We consider the problem of reinforcement learning (RL) with unbounded state space motivated by the classical problem of scheduling in a queueing network. Traditional policies as we…

cs.LG2020212 cited

Rethinking the Value of Labels for Improving Class-Imbalanced Learning

Yuzhe Yang, Zhi Xu

Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the va…

cs.LG20203 cited

On Reinforcement Learning for Turn-based Zero-sum Markov Games

Devavrat Shah, Varun Somani, Qiaomin Xie +1

We consider the problem of finding Nash equilibrium for two-player turn-based zero-sum games. Inspired by the AlphaGo Zero (AGZ) algorithm, we develop a Reinforcement Learning base…

cs.LG2019

Harnessing Structures for Value-Based Planning and Reinforcement Learning

Yuzhe Yang, Guo Zhang, Zhi Xu +1

Value-based methods constitute a fundamental methodology in planning and deep reinforcement learning (RL). In this paper, we propose to exploit the underlying structures of the sta…

cs.LG201959 cited

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

Yuzhe Yang, Guo Zhang, Dina Katabi +1

Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performan…