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 Huishuai Zhang

Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit


Jun 29, 2021
Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu


  Access Paper or Ask Questions

Large Scale Private Learning via Low-rank Reparametrization


Jun 28, 2021
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu

* Published as a conference paper in International Conference on Machine Learning (ICML 2021). Source code available at https://github.com/dayu11/Differentially-Private-Deep-Learning 

  Access Paper or Ask Questions

Adversarial Training with Rectified Rejection


May 31, 2021
Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu


  Access Paper or Ask Questions

Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning


Feb 26, 2021
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu

* Published as a conference paper at ICLR 2021. Source code available at https://github.com/dayu11/Gradient-Embedding-Perturbation 

  Access Paper or Ask Questions

BN-invariant sharpness regularizes the training model to better generalization


Jan 08, 2021
Mingyang Yi, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu

* Published in IJCAI2019 

  Access Paper or Ask Questions

Well-Conditioned Methods for Ill-Conditioned Systems: Linear Regression with Semi-Random Noise


Aug 04, 2020
Jerry Li, Aaron Sidford, Kevin Tian, Huishuai Zhang

* 31 pages, 4 figures 

  Access Paper or Ask Questions

Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary


Jul 21, 2020
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu


  Access Paper or Ask Questions

Adai: Separating the Effects of Adaptive Learning Rate and Momentum Inertia


Jul 17, 2020
Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama

* 25 pages, 8 figures 

  Access Paper or Ask Questions

On Layer Normalization in the Transformer Architecture


Feb 12, 2020
Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu


  Access Paper or Ask Questions

Gradient Perturbation is Underrated for Differentially Private Convex Optimization


Nov 26, 2019
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu, Jian Yin


  Access Paper or Ask Questions

Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data


May 29, 2019
Shicong Cen, Huishuai Zhang, Yuejie Chi, Wei Chen, Tie-Yan Liu


  Access Paper or Ask Questions

Training Over-parameterized Deep ResNet Is almost as Easy as Training a Two-layer Network


Mar 17, 2019
Huishuai Zhang, Da Yu, Wei Chen, Tie-Yan Liu

* 33 pages, 5 figures 

  Access Paper or Ask Questions

SGD Converges to Global Minimum in Deep Learning via Star-convex Path


Jan 02, 2019
Yi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh

* ICLR2019 

  Access Paper or Ask Questions

$\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space


Oct 09, 2018
Qi Meng, Wei Chen, Shuxin Zheng, Huishuai Zhang, Qiwei Ye, Zhi-Ming Ma, Tie-Yan Liu


  Access Paper or Ask Questions

Capacity Control of ReLU Neural Networks by Basis-path Norm


Sep 19, 2018
Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu


  Access Paper or Ask Questions

Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation


Feb 27, 2018
Huishuai Zhang, Wei Chen, Tie-Yan Liu

* 12 pages, 3 figures 

  Access Paper or Ask Questions

Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization


Feb 19, 2018
Yi Zhou, Yingbin Liang, Huishuai Zhang


  Access Paper or Ask Questions

Block-diagonal Hessian-free Optimization for Training Neural Networks


Dec 20, 2017
Huishuai Zhang, Caiming Xiong, James Bradbury, Richard Socher

* 10 pages, 3 figures 

  Access Paper or Ask Questions

Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent


Sep 23, 2017
Yuanxin Li, Yuejie Chi, Huishuai Zhang, Yingbin Liang

* 30 pages, 3 figures 

  Access Paper or Ask Questions

Median-Truncated Nonconvex Approach for Phase Retrieval with Outliers


May 18, 2017
Huishuai Zhang, Yuejie Chi, Yingbin Liang

* journal version under review 

  Access Paper or Ask Questions

Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations


Oct 27, 2016
Huishuai Zhang, Yi Zhou, Yingbin Liang, Yuejie Chi

* Part of this draft is accepted to NIPS 2016 

  Access Paper or Ask Questions