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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Does Network Width Really Help Adversarial Robustness?

Oct 03, 2020
Boxi Wu, Jinghui Chen, Deng Cai, Xiaofei He, Quanquan Gu

* 19 pages, 4 tables, 4 figures 

  Access Paper or Ask Questions

Efficient Robust Training via Backward Smoothing

Oct 03, 2020
Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu, Jingjing Liu

* 12 pages, 11 tables, 5 figures 

  Access Paper or Ask Questions

RayS: A Ray Searching Method for Hard-label Adversarial Attack

Jun 23, 2020
Jinghui Chen, Quanquan Gu

* 9 pages, 4 figures, 9 tables. In KDD 2020 

  Access Paper or Ask Questions

Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models

Mar 01, 2020
Xiao Zhang, Jinghui Chen, Quanquan Gu, David Evans

* 14 pages, 2 figures, 5 tables, AISTATS final paper reformatted for readability 

  Access Paper or Ask Questions

A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks

Nov 27, 2018
Jinghui Chen, Jinfeng Yi, Quanquan Gu

* 25 pages, 5 figures, 10 tables 

  Access Paper or Ask Questions

Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks

Jun 18, 2018
Jinghui Chen, Quanquan Gu

* 18 pages, 3 figures, 2 tables 

  Access Paper or Ask Questions

Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization

Feb 19, 2018
Pan Xu, Jinghui Chen, Difan Zou, Quanquan Gu

* 36 pages, 1 figure, 1 table 

  Access Paper or Ask Questions

Robust Wirtinger Flow for Phase Retrieval with Arbitrary Corruption

Jan 03, 2018
Jinghui Chen, Lingxiao Wang, Xiao Zhang, Quanquan Gu

* 29 pages, 5 figures, 2 tables 

  Access Paper or Ask Questions

High Dimensional Multivariate Regression and Precision Matrix Estimation via Nonconvex Optimization

Jun 02, 2016
Jinghui Chen, Quanquan Gu

* 32 pages, 5 figures, 3 tables 

  Access Paper or Ask Questions