Home
Biography
Publications
Teaching
Softwares
Activities

Shiqian Ma - Publications

  • ORCID: 0000-0003-1967-1069

  • My current research is supported by NSF grants DMS-1953210 and CCF-2007797, and UC Davis CeDAR (Center for Data Science and Artificial Intelligence Research) Innovative Data Science Seed Funding Program.

Preprints

  • Jiaxiang Li, Shiqian Ma. Federated Learning on Riemannian Manifolds. 2022. [link]

  • Xuxing Chen, Minhui Huang, Shiqian Ma. Decentralized Bilevel Optimization. 2022. [link]

  • Minhui Huang, Kaiyi Ji, Shiqian Ma and Lifeng Lai. Efficiently Escaping Saddle Points in Bilevel Optimization. 2022. [link]

  • Minhui Huang, Shiqian Ma and Lifeng Lai. On the Convergence of the Projected Alternating Maximization Algorithm for Equitable and Optimal Transport. 2021. [link]

  • Chao Zhang, Xiaojun Chen, Shiqian Ma. A Riemannian smoothing steepest descent method for non-Lipschitz optimization on submanifolds. 2021. [link]

  • Bo Jiang, Shiqian Ma, Anthony Man-Cho So and Shuzhong Zhang. Vector Transport-Free SVRG with General Retraction for Riemannian Optimization: Complexity Analysis and Practical Implementation. 2017. [link]

Journal Papers

  • Jiaxiang Li, Krishnakumar Balasubramanian, Shiqian Ma. Stochastic Zeroth-order Riemannian Derivative Estimation and Optimization. accepted in Mathematics of Operations Research. 2022. [link]

  • Zhongruo Wang, Krishnakumar Balasubramanian, Shiqian Ma, Meisam Razaviyayn. Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities. accepted in Journal of Global Optimization. 2022. [link]

  • Bokun Wang, Shiqian Ma, Lingzhou Xue. Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold. accepted in Journal of Machine Learning Research. 2022. [link]

  • Shixiang Chen, Zengde Deng, Shiqian Ma and Anthony Man-Cho So. Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning. IEEE Transactions on Signal Processing. 69: 4759-4773. 2021. [link].

  • Zhongruo Wang, Bingyuan Liu, Shixiang Chen, Shiqian Ma, Lingzhou Xue, Hongyu Zhao. A Manifold Proximal Linear Method for Sparse Spectral Clustering with Application to Single-Cell RNA Sequencing Data Analysis. accepted in INFORMS J. Optimization. 2021. [link]

  • Minhui Huang, Shiqian Ma, Lifeng Lai. Robust Low-Rank Matrix Completion via an Alternating Manifold Proximal Gradient Continuation Method. IEEE Transactions on Signal Processing. 69: 2639-2652. 2021. [link]

  • Shixiang Chen, Shiqian Ma, Anthony Man-Cho So and Tong Zhang. Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold. SIAM J. Optimization.30 (1): 210-239, 2020. [link] [code]

  • Junyu Zhang, Shiqian Ma and Shuzhong Zhang. Primal-Dual Optimization Algorithms over Riemannian Manifolds: an Iteration Complexity Analysis. Mathematical Programming Series A. 184: 445-490, 2020. [link]

  • Mingyi Hong, Tsung-Hui Chang, Xiangfeng Wang, Meisam Razaviyayn, Shiqian Ma and Zhi-Quan Luo. A Block Successive Upper Bound Minimization Method of Multipliers for Linearly Constrained Convex Optimization. Mathematics of Operations Research. 45 (3): 833-861. 2020. [link]

  • Shiqian Ma, Mingyi Hong. A Gentle Introduction to ADMM for Statistical Problems. Wiley StatsRef: Statistics Reference Online. 2021. [link]

  • Tianyi Lin, Shiqian Ma, Yinyu Ye and Shuzhong Zhang. An ADMM-Based Interior-Point Method for Large-Scale Linear Programming. Optimization Methods and Software. 36 (2-3): 389-424. 2021. [link] [code]

  • Shixiang Chen, Shiqian Ma, Lingzhou Xue and Hui Zou. An Alternating Manifold Proximal Gradient Method for Sparse Principal Component Analysis and Sparse Canonical Correlation Analysis. INFORMS J. Optimization. 2 (3): 192-208. 2020. [link] [Matlab codes] [R codes] [Python codes]

  • Conghui Tan, Yuqiu Qian, Shiqian Ma and Tong Zhang. Accelerated Dual-Averaging Primal-Dual Method for Composite Convex Minimization. Optimization Methods and Software. 35 (4): 741-766, 2020. [link]

  • Shiqian Ma, Fei Wang, Linchuan Wei and Henry Wolkowicz. Robust Principal Component Analysis using Facial Reduction. Optimization and Engineering. 21: 1195-1219. 2020. [link]

  • Ya-Feng Liu, Xin Liu and Shiqian Ma. On the non-ergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming. Mathematics of Operations Research. 44 (2): 632-650. 2019. [link] [arxiv]

  • Bo Jiang, Tianyi Lin, Shiqian Ma and Shuzhong Zhang. Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysis. Computational Optimization and Applications. 72 (1): 115-157, 2019. [link]

  • Bo Jiang, Shiqian Ma and Shuzhong Zhang. Low-M-Rank Tensor Completion and Robust Tensor PCA. IEEE Journal of Selected Topics in Signal Processing. 12 (6): 1390-1404. 2018. [link] (Previous title: New Ranks for Even-Order Tensors and Their Applications in Low-Rank Tensor Optimization. [link])

  • Shiqian Ma and Necdet Serhat Aybat. Efficient Optimization Algorithms for Robust Principal Component Analysis and Its Variants. Proceedings of the IEEE. 106 (8): 1411-1426. 2018. [link]

  • Jason Causey, Junyu Zhang, Shiqian Ma, Bo Jiang, Jake Qualls, David G. Politte, Fred Prior, Shuzhong Zhang and Xiuzhen Huang. Highly accurate model for prediction of lung nodule malignancy with CT scans. Scientific Reports. 8, Article number: 9286. 2018. [link]

  • Tianyi Lin, Shiqian Ma and Shuzhong Zhang. Global Convergence of Unmodified 3-Block ADMM for a Class of Convex Minimization Problems. Journal of Scientific Computing. 76 (1): 69-88, 2018. [link]

  • Yuwen Gu, Jun Fan, Lingchen Kong, Shiqian Ma and Hui Zou. ADMM for high-dimensional sparse penalized quantile regression. Technometrics. 60 (3): 319-331. 2018

  • Lei Yang, Junhui Wang and Shiqian Ma. Reduced-Rank Modeling for High-Dimensional Model-Based Clustering. Journal of Computational Mathematics, 36 (3): 428-442, 2018. (Invited paper on Special issue of International Workshop on Modern Optimization and Applications)

  • Necdet Serhat Aybat, Zi Wang, Tianyi Lin and Shiqian Ma. Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus Optimization. IEEE Transactions on Automatic Control. 63 (1): 5-20, 2018. [link]

  • Xiao Wang, Shiqian Ma, Donald Goldfarb and Wei Liu. Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization. SIAM Journal on Optimization. 27 (2): 927-956, 2017. [link] ( An earlier version is available here: [link])

  • Tianyi Lin, Shiqian Ma and Shuzhong Zhang. An Extragradient-Based Alternating Direction Method for Convex Minimization. Foundations of Computational Mathematics. 17 (1): 35-59, 2017. [link]

  • Xiao Wang, Shiqian Ma and Ya-xiang Yuan. Penalty Methods with Stochastic Approximation for Stochastic Nonlinear Programming. Mathematics of Computation. 86 (306): 1793-1820, 2017. [link]

  • Bo Jiang, Shiqian Ma, Jason Causey, Linbo Qiao, Matthew Price Hardin, Ian Bitts, Daniel Johnson, Shuzhong Zhang and Xiuzhen Huang. SparRec: An effective matrix completion framework of missing data imputation for GWAS. Scientific Reports. 6, Article number: 35534, 2016

  • Ya-Feng Liu, Shiqian Ma, Yu-Hong Dai and Shuzhong Zhang. A Smoothing SQP Framework for a Class of Composite L_q Minimization over Polyhedron. Mathematical Programming Series A. 158(1): 467-500, 2016. [link]

  • Shiqian Ma and Junfeng Yang. Applications of Gauge Duality in Robust Principal Component Analysis and Semidefinite Programming. Science China Mathematics. 59(8): 1579-1592, 2016. [link]

  • Tianyi Lin, Shiqian Ma and Shuzhong Zhang. Iteration Complexity Analysis of Multi-Block ADMM for a Family of Convex Minimization without Strong Convexity. Journal of Scientific Computing. 69: 52-81, 2016. [link]

  • Shiqian Ma. Alternating Proximal Gradient Method for Convex Minimization. Journal of Scientific Computing, 68(2): 546-572, 2016. [link]

  • Caihua Chen, Shiqian Ma and Junfeng Yang. A General Inertial Proximal Point Algorithm for Mixed Variational Inequality Problem. SIAM Journal on Optimization. 25 (4): 2120-2142, 2015. [link]

  • Caihua Chen, Raymond H. Chan, Shiqian Ma and Junfeng Yang. Inertial Proximal ADMM for Linearly Constrained Separable Convex Optimization. SIAM Journal on Imaging Sciences. 8 (4): 2239-2267, 2015. [link] (An earlier version is here: [link])

  • Tianyi Lin, Shiqian Ma and Shuzhong Zhang. On the Sublinear Convergence Rate of Multi-Block ADMM. Journal of the Operations Research Society of China. 3 (3): 251-274, 2015. [link] (Previous title: On the Convergence Rate of Multi-Block ADMM)

  • Tianyi Lin, Shiqian Ma and Shuzhong Zhang. On the Global Linear Convergence of the ADMM with Multi-Block Variables. SIAM Journal on Optimization. 25 (3): 1478-1497, 2015. [link]

  • Xiangfeng Wang, Mingyi Hong, Shiqian Ma and Zhi-Quan Luo. Solving Multiple-Block Separable Convex Minimization Problems Using Two-Block Alternating Direction Method of Multipliers. Pacific Journal of Optimization. 11 (4): 645-667, 2015. [link]

  • Ya-Feng Liu, Yu-Hong Dai and Shiqian Ma. Joint Power and Admission Control: Non-Convex L_q Approximation and An Effective Polynomial Time Deflation Approach. IEEE Transactions on Signal Processing. 63 (14): 3641-3656, 2015. [link]

  • S. Ma, D. Johnson, C. Ashby, D. Xiong, C.L. Cramer, J.H. Moore, S. Zhang, and X. Huang. SPARCoC: a new framework for molecular pattern discovery and cancer gene identification. PLoS ONE 10(3): e0117135, 2015. [link]

  • Zhiwei Qin, Donald Goldfarb and Shiqian Ma. An Alternating Direction Method for Total Variation Denoising. Optimization Methods and Software. 30 (3): 594-615, 2015. [link]

  • Bo Jiang, Shiqian Ma and Shuzhong Zhang. Tensor Principal Component Analysis via Convex Optimization. Mathematical Programming Series A. 150 (2): 423-457, 2015. [link]

  • Bo Jiang, Shiqian Ma and Shuzhong Zhang. Alternating Direction Method of Multipliers for Real and Complex Polynomial Optimization Models. Optimization. 63 (6): 883-898, 2014. [link]

  • Necdet Serhat Aybat, Donald Goldfarb and Shiqian Ma. Efficient Algorithms for Robust and Stable Principal Component Pursuit. Computational Optimization and Applications. 58: 1-29, 2014. [link]

  • Donald Goldfarb, Shiqian Ma and Katya Scheinberg. Fast Alternating Linearization Methods for Minimizing the Sum of Two Convex Functions. Mathematical Programming Series A, 141 (1-2): 349-382, 2013. [link]

  • Bo Huang, Shiqian Ma and Donald Goldfarb. Accelerated Linearized Bregman Method. Journal of Scientific Computing, 54 (2-3): 428-453, 2013. [link]

  • Shiqian Ma. Alternating Direction Method of Multipliers for Sparse Principal Component Analysis. Journal of the Operations Research Society of China, 1 (2): 253-274, 2013. (JORSC Excellent Paper Prize, Awarded in the Biennial Conference of Operations Research Society of China, 2016.) [link]

  • Shiqian Ma, Lingzhou Xue and Hui Zou. Alternating Direction Methods for Latent Variable Gaussian Graphical Model Selection. Neural Computation, 25 (8): 2172-2198, 2013. [link]

  • Lingzhou Xue, Shiqian Ma and Hui Zou. Positive Definite L1 Penalized Estimation of Large Covariance Matrices. Journal of the American Statistical Association, 107 (500): 1480-1491, 2012. [link]

  • Donald Goldfarb and Shiqian Ma. Fast Multiple-Splitting Algorithms for Convex Optimization. SIAM Journal on Optimization, 22 (2): 533-556, 2012. (INFORMS Optimization Society 2010 Best Student Paper Prize). [link]

  • Shiqian Ma, Donald Goldfarb and Lifeng Chen. Fixed Point and Bregman Iterative Methods for Matrix Rank Minimization. Mathematical Programming Series A. 128 (1): 321-353, 2011. [link]

  • Donald Goldfarb and Shiqian Ma. Convergence of Fixed-Point Continuation Algorithms for Matrix Rank Minimization. Foundations of Computational Mathematics. 11 (2): 183-210, 2011. [link]

  • Yanfei Wang and Shiqian Ma, A Fast Subspace Method for Image Deblurring. Applied Mathematics and Computation. 215 (6): 2359-2377, 2009.

  • Yanfei Wang, Shiqian Ma, Hua Yang, Jindi Wang and Xiaowen Li. On The Effective Inversion by Imposing a priori Information for Retrieval of Land Surface Parameters. Science in China Series D. 52 (4):540-549, 2009.

  • Yanfei Wang and Shiqian Ma, Projected Barzilai-Borwein Methods for Large Scale Nonnegative Image Restorations. Inverse Problems in Science and Engineering. 15 (6) : 559-583, 2007.

Conference Papers

  • Zhongruo Wang, Krishnakumar Balasubramanian, Shiqian Ma, Meisam Razaviyayn. Zeroth-Order Algorithms for Stochastic Nonconvex Minimax Problems with Improved Complexities. 2021 ICML workshop on “Beyond First-Order Methods in Machine Learning Systems” [link]

  • Minhui Huang, Shiqian Ma, Lifeng Lai. Projection Robust Wasserstein Barycenter. ICML. 2021. [link] [Python codes]

  • Minhui Huang, Shiqian Ma, Lifeng Lai. A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance. ICML. 2021. [link] [Python codes]

  • Shixiang Chen, Zengde Deng, Shiqian Ma and Anthony Man-Cho So. Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning. Asilomar Conference on Signals, Systems, and Computers. 2019. [link].

  • Conghui Tan, Tong Zhang, Shiqian Ma and Ji Liu. Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity. NIPS. 2018. [link]

  • Shixiang Chen, Shiqian Ma and Wei Liu. Geometric descent method for convex composite minimization. NIPS. 2017. [link]

  • Li Shen, Wei Liu, Ganzhao Yuan and Shiqian Ma. GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-term Nonsmooth Convex Composite Optimization. ICML. 2017. [link]

  • Li Shen, Wei Liu, Junzhou Huang, Yugang Jiang and Shiqian Ma. Adaptive Proximal Average Approximation for Composite Convex Minimization. AAAI. 2017. [link]

  • Conghui Tan, Shiqian Ma, Yu-Hong Dai and Yuqiu Qian. Barzilai-Borwein Step Size for Stochastic Gradient Descent. NIPS. 2016. [link] [code]

  • Xiao Wen, Linbo Qiao, Shiqian Ma, Wei Liu, Hong Cheng. Sparse Subspace Clustering for Incomplete Images. ICCV Workshop on Robust Subspace Learning and Computer Vision. 2015.

  • Wei Liu, Cun Mu, Rongrong Ji, Shiqian Ma, John R. Smith, Shih-Fu Chang. Low-Rank Similarity Metric Learning in High Dimensions. AAAI. 2015.

  • Weiwei Shen, Jun Wang and Shiqian Ma. Doubly Regularized Portfolio with Risk Minimization. AAAI. 2014.

  • Mingyi Hong, Tsung-Hui Chang, Xiangfeng Wang, Meisam Razaviyayn, Shiqian Ma, Zhi-Quan Luo. A block coordinate descent method of multipliers: Convergence Analysis and Applications. ICASSP. 2014.

  • Shiqian Ma and Amit Chakraborty. Reconstructing A Sequence of Magnetic Resonance Images Simultaneously Using Low-Rank and Sparse Model. IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA). 2012.

  • Katya Scheinberg, Shiqian Ma and Donald Goldfarb. Sparse Inverse Covariance Selection via Alternating Linearization Methods. Twenty-Fourth Annual Conference on Neural Information Processing Systems (NIPS). 2010. [link]

  • Wei Liu, Shiqian Ma, Dacheng Tao, Jianzhuang Liu and Peng Liu. Semi-Supervised Sparse Metric Learning using Alternating Linearization Optimization. The Sixteenth ACM SIGKDD International Conference On Knowledge Discovery and Data Mining (SIGKDD). 2010.

  • Donald Goldfarb, Shiqian Ma and Zaiwen Wen. Solving Low-Rank Matrix Completion Problems Efficiently. Invited paper at the 47th Allerton Conference on Communication, Control and Computing, Illinois, 2009

  • Shiqian Ma, Wotao Yin, Yin Zhang and Amit Chakraborty. An Efficient Algorithm for Compressed MR Imaging Using Total Variation and Wavelets, IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2008.

  • Yanfei Wang, Xiaowen Li, Shiqian Ma, Hua Yang, Zuhair Nashed and Yanning Guan. BRDF Model Inversion of Multiangular Remote Sensing: Ill-posedness and the Interior Point Solution Method. Proceedings of the 9th International Symposium on Physical Measurements and Signatures in Remote Sensing (ISPMSRS), Vol. XXXVI : 328-330, 2005.

Book Chapters

  • Shiqian Ma, Bo Jiang, Xiuzhen Huang, and Shuzhong Zhang. Tensor Models: Solution Methods and Applications. Chapter in “Big Data over Networks”, editors: Shuguang (Robert) Cui, Alfred O. Hero III, Zhi-Quan (Tom) Luo, and Jose M. F. Moura. Cambridge University Press. 2015

  • Katya Scheinberg and Shiqian Ma. Optimization Methods for Sparse Inverse Covariance Selection. in Suvrit Sra, Sebastian Nowozin, and Stephen J. Wright. editors: Optimization for Machine Learning, MIT Press, 2011

  • Yanfei Wang, Shiqian Ma and Qinghua Ma. Full Space and Subspace Methods for Large Scale Image Restoration. in Y. F. Wang, A. G. Yagola and C. C. Yang editors: Optimization and Regularization for Computational Inverse Problems and Applications, Beijing/Berlin: Higher Education Press and Springer, 2010

Newsletter

  • Shiqian Ma. Fast Multiple Splitting Algorithms for Convex Optimization. INFORMS OS Today, The Newsletter of the INFORMS Optimization Society. 2011 [link]

Technical Reports

  • Zaiwen Wen, Donald Goldfarb, Shiqian Ma and Katya Scheinberg. Row by Row Methods for Semidefinite Programming. Technical Report, Columbia University. 2009 [link]