Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zhun Deng

Understanding Dynamics of Nonlinear Representation Learning and Its Application


Jun 28, 2021
Kenji Kawaguchi, Linjun Zhang, Zhun Deng


  Access Paper or Ask Questions

Adversarial Training Helps Transfer Learning via Better Representations


Jun 18, 2021
Zhun Deng, Linjun Zhang, Kailas Vodrahalli, Kenji Kawaguchi, James Zou


  Access Paper or Ask Questions

When and How Mixup Improves Calibration


Feb 11, 2021
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, James Zou


  Access Paper or Ask Questions

Toward Better Generalization Bounds with Locally Elastic Stability


Oct 27, 2020
Zhun Deng, Hangfeng He, Weijie J. Su


  Access Paper or Ask Questions

Towards Understanding the Dynamics of the First-Order Adversaries


Oct 20, 2020
Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie J. Su


  Access Paper or Ask Questions

How Does Mixup Help With Robustness and Generalization?


Oct 09, 2020
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

Interpreting Robust Optimization via Adversarial Influence Functions


Oct 03, 2020
Zhun Deng, Cynthia Dwork, Jialiang Wang, Linjun Zhang


  Access Paper or Ask Questions

Decision-Aware Conditional GANs for Time Series Data


Sep 30, 2020
He Sun, Zhun Deng, Hui Chen, David C. Parkes


  Access Paper or Ask Questions

Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations


Jun 20, 2020
Zhun Deng, Frances Ding, Cynthia Dwork, Rachel Hong, Giovanni Parmigiani, Prasad Patil, Pragya Sur


  Access Paper or Ask Questions

Improving Adversarial Robustness via Unlabeled Out-of-Domain Data


Jun 15, 2020
Zhun Deng, Linjun Zhang, Amirata Ghorbani, James Zou


  Access Paper or Ask Questions

Architecture Selection via the Trade-off Between Accuracy and Robustness


Jun 04, 2019
Zhun Deng, Cynthia Dwork, Jialiang Wang, Yao Zhao


  Access Paper or Ask Questions