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
Deep Networks from the Principle of Rate Reduction

Oct 27, 2020
Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma


  Access Paper or Ask Questions

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients

Sep 28, 2020
Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao

* 16 pages 

  Access Paper or Ask Questions

Boundary thickness and robustness in learning models

Jul 09, 2020
Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney


  Access Paper or Ask Questions

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Jun 15, 2020
Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma


  Access Paper or Ask Questions

Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

Mar 21, 2020
Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma


  Access Paper or Ask Questions

Theoretically Principled Trade-off between Robustness and Accuracy

Jan 24, 2019
Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan

* Technical details of the winning entry to the NeurIPS 2018 Adversarial Vision Challenge 

  Access Paper or Ask Questions

Learning One-hidden-layer ReLU Networks via Gradient Descent

Jun 20, 2018
Xiao Zhang, Yaodong Yu, Lingxiao Wang, Quanquan Gu

* 26 pages, 2 figures 

  Access Paper or Ask Questions

Third-order Smoothness Helps: Even Faster Stochastic Optimization Algorithms for Finding Local Minima

Dec 18, 2017
Yaodong Yu, Pan Xu, Quanquan Gu

* 25 pages 

  Access Paper or Ask Questions

Saving Gradient and Negative Curvature Computations: Finding Local Minima More Efficiently

Dec 11, 2017
Yaodong Yu, Difan Zou, Quanquan Gu

* 31 pages, 1 table 

  Access Paper or Ask Questions