About Me

I am a tenure-track assistant professor at the Department of Computer Science, Stevens Institute of Technology. From 2016 to 2018, I was a postdoc scholar at Department of Statistics, UC Berkeley. I worked with Michael Mahoney. In 2011 and 2016, I got both of my doctoral and bachelor's degrees from Zhejiang University, China, where I worked with my advisor Zhihua Zhang. During my doctoral study, I was supported by "Microsoft Research Asia Fellowship" and "Baidu Scholarship", which are (or at least were) the highest fellowships/scholarships in China.

Research Interest

Machine learning

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

Distributed learning, federated learning, and general large-scale machine learning.

Learning from complex data.

Randomized numerical linear algebra

Matrix sketching and randomized matrix computation.

Applications to statistical learning theory.

Applications to scalable machine learning algorithms.

Distributed computing

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

Major Experience

Department of Computer Science, Stevens Institute of Technology, from 09/2018

tenure-track assistant professor

Department of Statistics, UC Berkeley, 07/2016---06/2018

postdoc researcher, with Michael Mahoney

Zhejiang University, Doctor of Engineering, 09/2011---06/2016

College of Computer Science and Techonology

Zhejiang University, Bachelor of Engineering, 08/2007---07/2011

College of Computer Science and Techonology

Chu Kochen Honors College

Graduate with "the 100 Best Bachelor Theses Award"

Representative Papers [Full List] [Google Scholar]

  • A Bootstrap Method for Error Estimation in Randomized Matrix Multiplication.
    Miles E. Lopes, Shusen Wang, Michael W. Mahoney.
    Journal of Machine Learning Research (JMLR), 20(39):1-40, 2019.
    [pdf] [bib] [arXiv:1708.01945].

  • Scalable Kernel K-Means Clustering with Nystrom Approximation: Relative-Error Bounds.
    Shusen Wang, Alex Gittens, and Michael W. Mahoney.
    Journal of Machine Learning Research (JMLR), 20(12):1-49, 2019.
    [pdf] [bib] [arXiv:1706.02803]

  • Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging.
    Shusen Wang, Alex Gittens, and Michael W. Mahoney.
    Journal of Machine Learning Research (JMLR), 18(218):1-50, 2018.
    A short version has appeared in ICML 2017. (There are errors in the ICML version; please refer to the journal version for the correct results.)
    [pdf] [bib]

  • Towards More Efficient SPSD Matrix Approximation and CUR Matrix Decomposition.
    Shusen Wang, Zhihua Zhang, and Tong Zhang.
    Journal of Machine Learning Research (JMLR), 17(210):1−49, 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 (JMLR), 17(49):1-49, 2016.
    Short versions have appeared in AISTATS 2014 and KDD 2014.
    [pdf] [bib]

  • Improving CUR Matrix Decomposition and the Nystrom Approximation via Adaptive Sampling.
    Shusen Wang and Zhihua Zhang.
    Journal of Machine Learning Research (JMLR), 14: 2729-2769, 2013.
    A short version has appeared in NIPS 2012.
    [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 (JMLR), 13: 2031-2061, 2012.
    [pdf] [bib]

  • GIANT: Globally Improved Approximate Newton Method for Distributed Optimization.
    Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, and Michael W. Mahoney.
    In 32nd Conference on Neural Information Processing Systems (NIPS), 2018.
    [pdf] [bib] [long version] [Spark Code].

Recent Talks

Flag Counter

Last update: 2019-04-03