**Click to Read Paper**

From Adversarial Training to Generative Adversarial Networks

Aug 03, 2018

Xuanqing Liu, Cho-Jui Hsieh

Aug 03, 2018

Xuanqing Liu, Cho-Jui Hsieh

* NIPS 2018 submission, under review. v2: More experiments on comparing inception score, release code and some minor fixes

**Click to Read Paper**

RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications

Oct 28, 2018

Huan Zhang, Pengchuan Zhang, Cho-Jui Hsieh

Oct 28, 2018

Huan Zhang, Pengchuan Zhang, Cho-Jui Hsieh

* Work done during internship at Microsoft Research

**Click to Read Paper**

**Click to Read Paper**

Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient

Sep 26, 2018

Liu Liu, Xuanqing Liu, Cho-Jui Hsieh, Dacheng Tao

Sep 26, 2018

Liu Liu, Xuanqing Liu, Cho-Jui Hsieh, Dacheng Tao

**Click to Read Paper**

Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem

Sep 06, 2018

Liu Liu, Ji Liu, Cho-Jui Hsieh, Dacheng Tao

Sep 06, 2018

Liu Liu, Ji Liu, Cho-Jui Hsieh, Dacheng Tao

**Click to Read Paper**

SQL-Rank: A Listwise Approach to Collaborative Ranking

Sep 04, 2018

Liwei Wu, Cho-Jui Hsieh, James Sharpnack

Sep 04, 2018

Liwei Wu, Cho-Jui Hsieh, James Sharpnack

**Click to Read Paper**

Communication-Efficient Parallel Block Minimization for Kernel Machines

Aug 05, 2016

Cho-Jui Hsieh, Si Si, Inderjit S. Dhillon

Aug 05, 2016

Cho-Jui Hsieh, Si Si, Inderjit S. Dhillon

**Click to Read Paper**

A Divide-and-Conquer Solver for Kernel Support Vector Machines

Nov 04, 2013

Cho-Jui Hsieh, Si Si, Inderjit S. Dhillon

Nov 04, 2013

Cho-Jui Hsieh, Si Si, Inderjit S. Dhillon

**Click to Read Paper**

Stochastic Zeroth-order Optimization via Variance Reduction method

Aug 02, 2018

Liu Liu, Minhao Cheng, Cho-Jui Hsieh, Dacheng Tao

Aug 02, 2018

Liu Liu, Minhao Cheng, Cho-Jui Hsieh, Dacheng Tao

**Click to Read Paper**

History PCA: A New Algorithm for Streaming PCA

Feb 15, 2018

Puyudi Yang, Cho-Jui Hsieh, Jane-Ling Wang

In this paper we propose a new algorithm for streaming principal component analysis. With limited memory, small devices cannot store all the samples in the high-dimensional regime. Streaming principal component analysis aims to find the $k$-dimensional subspace which can explain the most variation of the $d$-dimensional data points that come into memory sequentially. In order to deal with large $d$ and large $N$ (number of samples), most streaming PCA algorithms update the current model using only the incoming sample and then dump the information right away to save memory. However the information contained in previously streamed data could be useful. Motivated by this idea, we develop a new streaming PCA algorithm called History PCA that achieves this goal. By using $O(Bd)$ memory with $B\approx 10$ being the block size, our algorithm converges much faster than existing streaming PCA algorithms. By changing the number of inner iterations, the memory usage can be further reduced to $O(d)$ while maintaining a comparable convergence speed. We provide theoretical guarantees for the convergence of our algorithm along with the rate of convergence. We also demonstrate on synthetic and real world data sets that our algorithm compares favorably with other state-of-the-art streaming PCA methods in terms of the convergence speed and performance.
Feb 15, 2018

Puyudi Yang, Cho-Jui Hsieh, Jane-Ling Wang

**Click to Read Paper**

PU Learning for Matrix Completion

Nov 22, 2014

Cho-Jui Hsieh, Nagarajan Natarajan, Inderjit S. Dhillon

Nov 22, 2014

Cho-Jui Hsieh, Nagarajan Natarajan, Inderjit S. Dhillon

**Click to Read Paper**

Block-wise Partitioning for Extreme Multi-label Classification

Nov 04, 2018

Yuefeng Liang, Cho-Jui Hsieh, Thomas C. M. Lee

Nov 04, 2018

Yuefeng Liang, Cho-Jui Hsieh, Thomas C. M. Lee

**Click to Read Paper**

Attack Graph Convolutional Networks by Adding Fake Nodes

Oct 26, 2018

Xiaoyun Wang, Joe Eaton, Cho-Jui Hsieh, Felix Wu

Oct 26, 2018

Xiaoyun Wang, Joe Eaton, Cho-Jui Hsieh, Felix Wu

**Click to Read Paper**

Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network

Oct 01, 2018

Xuanqing Liu, Yao Li, Chongruo Wu, Cho-Jui Hsieh

Oct 01, 2018

Xuanqing Liu, Yao Li, Chongruo Wu, Cho-Jui Hsieh

* Code will be made available at https://github.com/xuanqing94/BayesianDefense

**Click to Read Paper**

RedSync : Reducing Synchronization Traffic for Distributed Deep Learning

Aug 13, 2018

Jiarui Fang, Haohuan Fu, Guangwen Yang, Cho-Jui Hsieh

Aug 13, 2018

Jiarui Fang, Haohuan Fu, Guangwen Yang, Cho-Jui Hsieh

* 20 pages

**Click to Read Paper**

Towards Robust Neural Networks via Random Self-ensemble

Aug 01, 2018

Xuanqing Liu, Minhao Cheng, Huan Zhang, Cho-Jui Hsieh

Aug 01, 2018

Xuanqing Liu, Minhao Cheng, Huan Zhang, Cho-Jui Hsieh

* ECCV 2018 camera ready

**Click to Read Paper**

PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent

Apr 06, 2015

Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit S. Dhillon

Apr 06, 2015

Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit S. Dhillon

**Click to Read Paper**

ImageNet Training in Minutes

Jan 31, 2018

Yang You, Zhao Zhang, Cho-Jui Hsieh, James Demmel, Kurt Keutzer

Jan 31, 2018

Yang You, Zhao Zhang, Cho-Jui Hsieh, James Demmel, Kurt Keutzer

**Click to Read Paper**

An inexact subsampled proximal Newton-type method for large-scale machine learning

Aug 28, 2017

Xuanqing Liu, Cho-Jui Hsieh, Jason D. Lee, Yuekai Sun

Aug 28, 2017

Xuanqing Liu, Cho-Jui Hsieh, Jason D. Lee, Yuekai Sun

**Click to Read Paper**