About Me

I am postdoc scholar at Department of Statistics, UC Berkeley. I work with Michael Mahoney. Before that, I got both of my doctoral and bachelor's degree from Zhejiang University, China. My advisor was Zhihua Zhang. During my doctoral study, I have been supported by "the Microsoft Research Asia Fellowship" and "Baidu Scholarship", which were the highest fellowships/scholarships in China.

Research Interest

Machine learning

Computational methods such as numerical optimization, matrix computation, bootstrap, etc.

Regression, clustering, dimensionality reduction, kernel methods, Bayesian methods.

Randomized numerical linear algebra

Matrix sketching, randomized matrix computation, kernel approximation, etc.

Distributed computing

The design, analysis, and implementation of distributed algorithms (for machine learning and optimization).


Zhejiang University, Doctor of Engineering, 2011---2016

College of Computer Science and Techonology

Zhejiang University, Bachelor of Engineering, 2007---2011

College of Computer Science and Techonology

Chu Kochen Honors College

Graduate with "the 100 Best Bachelor Theses Award"

Work Experience

Department of Statistics, UC Berkeley, 07/2016---Now

postdoc researcher, with Michael Mahoney

Baidu Big Data Lab, Beijing, China, 05/2014---08/2015

research intern, with Prof. Tong Zhang

Google Research, Beijing, China, 02/2012---08/2012

research intern

Microsoft Research Asia, Beijing, China, 08/2011---02/2012

intern, with Dr. Haixun Wang and Dr. Yangqiu Song

Representative Papers [Full List] [Google Scholar]

  • Scalable Kernel K-Means Clustering with Nystrom Approximation: Relative-Error Bounds.
    Shusen Wang, Alex Gittens, and Michael W. Mahoney.
    Accepted by Journal of Machine Learning Research (JMLR), conditioned on minor revisions.

  • GIANT: Globally Improved Approximate Newton Method for Distributed Optimization.
    Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, and Michael W. Mahoney.
    arXiv:1709.03528, 2017.
    [Spark Code] [Large-Scale Experiments]

  • Towards More Efficient SPSD Matrix Approximation and CUR Matrix Decomposition.
    Shusen Wang, Zhihua Zhang, and Tong Zhang.
    Journal of Machine Learning Research, 17(210):1−49, 2016. (JMLR 2016).
    [pdf] [bib]

  • SPSD Matrix Approximation vis Column Selection: Theories, Algorithms, and Extensions.
    Shusen Wang, Luo Luo, and Zhihua Zhang.
    Journal of Machine Learning Research, 17(49):1-49, 2016. (JMLR 2016).
    [pdf] [bib]

  • Improving CUR Matrix Decomposition and the Nystrom Approximation via Adaptive Sampling.
    Shusen Wang and Zhihua Zhang.
    Journal of Machine Learning Research, 14: 2729-2769, 2013. (JMLR 2013).
    [pdf] [bib]

  • EP-GIG Priors and Applications in Bayesian Sparse Learning.
    Zhihua Zhang, Shusen Wang, Dehua Liu, and Michael I. Jordan.
    Journal of Machine Learning Research, 13: 2031-2061, 2012. (JMLR 2012).
    [pdf] [bib]

Honors & Awards

Baidu Scholarship, 2014

award to 8 Chinese students around the world, CNY 200,000

Microsoft Research Asia Fellow, 2013

award to 10 students in Asia Pacific, USD 10,000

Scholarship Award for Excellent Doctoral Student Granted by Ministry of Education, 2012

award to 25 PhD students from all majors in Zhejiang University, CNY 30,000

National Scholarship for Graduate Students, 3 times, 2012-2014

CNY 30,000 each time

Recent Talks

Flag Counter

Last update: 2017-11-03