Journal Papers

  • Fast Randomized-MUSIC for Mm-Wave Massive MIMO Radars.
    Bin Li, Shusen Wang, Jun Zhang, Xianbin Cao, and Chenglin Zhao.
    IEEE Transactions on Vehicular Technology, 70(2):1952-1956, 2021.

  • Fast Pseudo-spectrum Estimation for Automotive Massive MIMO Radar.
    Bin Li, Shusen Wang, Zhiyong Feng, Jun Zhang, Xianbin Cao, and Chenglin Zhao.
    IEEE Internet of Things Journal, 2021.

  • Randomized Approximate Channel Estimator in Massive-MIMO Communication.
    Bin Li, Shusen Wang, Xianbin Cao, Jun Zhang, and Chenglin Zhao.
    IEEE Communications Letters, 2020.

  • 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]

  • Alchemist: An Apache Spark <=> MPI Interface .
    Alex Gittens, Kai Rothauge, Shusen Wang, Michael W. Mahoney, Jey Kottalam, Lisa Gerhardt, Prabhat, Michael Ringenburg, and Kristyn Maschhoff.
    Concurrency and Computation: Practice and Experience (CCPE), 31(16), e5026, 2019.
    [pdf] [bib]

  • Efficient Data-Driven Geologic Feature Characterization from Pre-stack Seismic Measurements using Randomized Machine-Learning Algorithm.
    Youzuo Lin, Shusen Wang, Jayaraman Thiagarajan, George Guthrie, and David Coblentz.
    Geophysical Journal International, ggy385, 2018.
    [pdf] [bib]

  • 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]

Preprints

  • Privacy-Preserving Distributed SVD via Federated Power.
    Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, Zhihua Zhang.
    arXiv:2103.00704, 2021.

  • Communication Efficient Decentralized Training with Multiple Local Updates.
    Xiang Li, Wenhao Yang, Shusen Wang, and Zhihua Zhang.
    arXiv:1910.09126, 2019.

  • Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping.
    Shusen Wang.
    arXiv:1909.11207, 2019.

  • Fast Generalized Matrix Regression with Applications in Machine Learning.
    Haishan Ye, Shusen Wang, Zhihua Zhang, and Tong Zhang.
    arXiv:1912.12008, 2019.

  • Improved Analyses of the Randomized Power Method and Block Lanczos Method.
    Shusen Wang, Zhihua Zhang, and Tong Zhang.
    arXiv:1508.06429, 2015.

Conference Papers

  • Matrix Sketching for Secure Collaborative Machine Learning.
    Mengjiao Zhang and Shusen Wang.
    In International Conference on Machine Learning (ICML), 2021.
    [pdf] [bib]

  • Communication-Efficient Distributed SVD via Local Power Iterations.
    Xiang Li, Shusen Wang, Kun Chen, and Zhihua Zhang.
    In International Conference on Machine Learning (ICML), 2021.
    [pdf] [bib]

  • Accelerating Transformer-based Deep Learning Models on FPGAs using Column Balanced Block Pruning.
    Hongwu Peng, Shaoyi Huang, Tong Geng, Ang Li, Weiwen Jiang, Hang Liu, Shusen Wang, Caiwen Ding.
    In International Symposium on Quality Electronic Design, 2021.
    [pdf]

  • On the Convergence of FedAvg on Non-IID Data.
    Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang.
    In International Conference on Learning Representations (ICLR), 2020.
    [pdf] [bib]

  • Do Subsampled Newton Methods Work for High-Dimensional Data?
    Xiang Li, Shusen Wang, and Zhihua Zhang.
    In AAAI Conference on Artificial Intelligence (AAAI), 2020.
    [pdf] [bib]

  • Cola-GNN: Cross-location Attention based Graph Neural Networks for Long-term ILI Prediction.
    Songgaojun Deng, Shusen Wang, Huzefa Rangwala, Lijing Wang, and Yue Ning.
    In ACM International Conference on Information and Knowledge Management (CIKM), 2020.

  • A Sharper Generalization Bound for Divide-and-Conquer Ridge Regression.
    Shusen Wang.
    In AAAI Conference on Artificial Intelligence (AAAI), 2019.
    [pdf] [bib]

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

  • Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap.
    Miles E. Lopes, Shusen Wang, Michael W. Mahoney.
    In International Conference on Machine Learning (ICML), 2018.
    [pdf] [long version]

  • Accelerating Large-Scale Data Analysis by Offloading to High-Performance Computing Libraries using Alchemist.
    Alex Gittens, Kai Rothauge, Shusen Wang, Michael W. Mahoney, Lisa Gerhardt, Prabhat, Jey Kottalam, Michael Ringenburg, and Kristyn Maschhoff.
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2018.
    [pdf] [bib]

  • OverSketch: Approximate Matrix Multiplication for the Cloud.
    Vipul Gupta, Shusen Wang, Thomas Courtade, and Kannan Ramchandran.
    In IEEE International Conference on Big Data, 2018.
    [pdf] [bib]

  • Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging.
    Shusen Wang, Alex Gittens, and Michael W. Mahoney.
    In International Conference on Machine Learning (ICML), 2017.
    [pdf] [bib] [long version]

  • Towards Real-Time Geologic Feature Detection from Seismic Measurements using a Randomized Machine-Learning Algorithm.
    Youzuo Lin, Shusen Wang, Jayaraman Thiagarajan, George Guthrie, and David Coblentz.
    In Proceeding of Society of Exploration Geophysics (SEG), 2017.

  • Open Domain Short Text Conceptualization: A Generative + Descriptive Modeling Approach.
    Yangqiu Song, Shusen Wang, and Haixun Wang.
    In International Joint Conference on Artificial Intelligence (IJCAI), 2015.
    [pdf]

  • Improving the Modified Nystrom Method Using Spectral Shifting.
    Shusen Wang, Chao Zhang, Hui Qian, and Zhihua Zhang.
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2014.
    [pdf]

  • Efficient Algorithms and Error Analysis for the Modified Nystrom Method.
    Shusen Wang and Zhihua Zhang.
    In International Conference on Artificial Intelligence and Statistics (AISTATS), 2014.
    [arXiv:1404.0138] [bib] [code] [slides]

  • Making Fisher Discriminant Analysis Scalable.
    Bojun Tu, Zhihua Zhang, Shusen Wang, and Hui Qian.
    In International Conference on Machine Learning (ICML), 2014.
    [pdf] [bib]

  • Exact Subspace Clustering in Linear Time.
    Shusen Wang, Bojun Tu, Congfu Xu, and Zhihua Zhang.
    In AAAI Conference on Artificial Intelligence (AAAI), 2014.
    [pdf] [bib]

  • Using The Matrix Ridge Approximation to Speedup Determinantal Point Processes Sampling Algorithms.
    Shusen Wang, Chao Zhang, Hui Qian, and Zhihua Zhang.
    In AAAI Conference on Artificial Intelligence (AAAI), 2014.
    [pdf] [bib]

  • Transfer Understanding from Head Queries to Tail Queries.
    Yangqiu Song, Haixun Wang, Weizhu Chen, and Shusen Wang.
    In ACM International Conference on Information and Knowledge Management (CIKM), 2014.
    [pdf]

  • Nonconvex Relaxation Approaches to Robust Matrix Recovery.
    Shusen Wang, Dehua Liu, and Zhihua Zhang.
    In International Joint Conference on Artificial Intelligence (IJCAI), 2013.
    [pdf] [bib] [code] [slides] [poster]

  • A Scalable CUR Matrix Decomposition Algorithm: Lower Time Complexity and Tighter Bound.
    Shusen Wang and Zhihua Zhang.
    In Advances in Neural Information Processing Systems (NIPS), 2012.
    [pdf] [bib] [code]

  • Colorization by Matrix Completion.
    Shusen Wang and Zhihua Zhang.
    In AAAI Conference on Artificial Intelligence (AAAI), 2012.
    [pdf] [bib] [code] [data] [poster]

  • Efficient Subspace Segmentation via Quadratic Programming.
    Shusen Wang, Xiaotong Yuan, Tiansheng Yao, Shuicheng Yan, and Jialie Shen.
    In AAAI Conference on Artificial Intelligence (AAAI), 2011.
    [pdf] [bib] [code]

Book

  • Deep Reinforcement Learning (Chinese).
    Shusen Wang and Zhihua Zhang.
    Draft: [click here]