activity
20172022
most citedRethinking the Value of Labels for Improving Class-Imbalanced Learning

212 citations · 290 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG20223 cited

Domain Adaptation with Factorizable Joint Shift

Hao He, Yuzhe Yang, Hao Wang

Existing domain adaptation (DA) usually assumes the domain shift comes from either the covariates or the labels. However, in real-world applications, samples selected from differen…

cs.LG2021

Delving into Deep Imbalanced Regression

Yuzhe Yang, Kaiwen Zha, Ying-Cong Chen +2

Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focu…

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.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.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…