Publications

Books

Review papers

  • X. Liu, Z. Wen, Y. Yuan, Subspace Methods for Nonlinear Optimization, CSIAM Transactions on Applied Mathematics (paper)

  • 潘少华, 文再文, 低秩稀疏矩阵优化问题的模型与算法, 运筹学学报 (paper)
    S. Pan, Z. Wen, Models and Algorithms for Low-rank and Sparse Matrix Optimization Problems (in Chinese), Operations Research Transactions (paper)

  • J. Hu, X. Liu, Z. Wen, Y. Yuan, A Brief Introduction to Manifold Optimization, Journal of Operations Research Society of China, (paper)

  • 王奇超,文再文,蓝光辉,袁亚湘, 优化算法复杂度分析, 中国科学:数学 (paper)
    Q. Wang, Z. Wen, G. Lan, Y. Yuan, Complexity Analysis For Optimization Methods (in Chinese), SCIENTIA SINICA Mathematica, (paper)

Selected papers

  • Z. Xie, W. Yin, Z. Wen, ODE-based Learning to Optimize, (paper), (code: “O2O”)

  • Y. Chen, L. Cao, K. Yuan, Z. Wen, Sharper Convergence Guarantees for Federated Learning with Partial Model Personalization, (paper)

  • R. Wang, C. Zhang, S. Pu, J. Gao, Z. Wen, A Customized Augmented Lagrangian Method for Block-Structured Integer Programming, IEEE Transactions on Pattern Analysis and Machine Intelligence, (paper)

  • J. Wu, J. Hu, H. Zhang, Z. Wen, Convergence analysis of an adaptively regularized natural gradient method, IEEE Transactions on Signal Processing, 2024

  • Z. Ke, J. Zhang, Z. Wen, An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks, ICML 2024

  • Z. Deng, K. Deng, J. Hu, Z. Wen, An Augmented Lagrangian Primal-Dual Semismooth Newton Method for Multi-Block Composite Optimization (paper)

  • C. Chen, R. Chen, T. Li, R. Ao, Z. Wen, A Monte Carlo Policy Gradient Method with Local Search for Binary Optimization, (paper) (code: “MCPG”)

  • T. Li, F. Chen, H. Chen, Z. Wen, Provable Convergence of Variational Monte Carlo Methods (paper)

  • Z. Ke, J. Zhang, Z. Wen, Gauss-Newton Temporal Difference Learning with Nonlinear Function Approximation (paper)

  • J. Hu, T. Tian, S. Pan, Z. Wen, On the local convergence of the semismooth Newton method for composite optimization, (paper)

  • L. Cao, Z. Wen, Y. Yuan, Some Sharp Error Bounds for Multivariate Linear Interpolation and Extrapolation, (paper)

  • Z. Zhu, F. Chen, J. Zhang, Z. Wen, A Unified Primal-Dual Algorithm Framework for Inequality Constrained Problems, Journal of Scientific Computing, 2023, (paper)

  • J. Hu, R. Ao, A. So, M. Yang, Z. Wen, Riemannian Natural Gradient Methods, SIAM Journal on Scientific Computing, (paper)

  • Y. Liu, H. Liu, H. Nie, Z. Wen, A DRS-based Path-following Algorithm for Linear Programming

  • F. Chen, J. Zhang, Z. Wen, A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP, NeurIPS 2022, (paper)

  • Y. Wang, K. Deng, H. Liu, Z. Wen, A Decomposition Augmented Lagrangian Method for Low-rank Semidefinite Programming, SIAM Journal on Optimization, (paper)

  • H. Liu, K. Deng, H. Liu, Z. Wen, An Entropy-Regularized ADMM For Binary Quadratic Programming, Journal of Global Optimization

  • J. Zhang, Z. Jin, B. Jiang, Z. Wen, Stochastic Augmented Projected Gradient Methods for the Large-Scale Precoding Matrix Indicator Selection Problem, IEEE Transactions on Wireless Communications

  • M. Yang, D. Xu, Q. Cui, Z. Wen, P. Xu, NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, (paper) (code)

  • Y. Liu, Z. Wen, W. Yin, A multiscale semi-smooth Newton method for Optimal Transport, Journal of Scientific Computing

  • Y. Li, M. Zhao, W. Chen, Z. Wen, A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning, SIAM Journal on Optimization, (paper)

  • Z. Jin, J. Schmitt, Z. Wen, On the Analysis of Model-free Methods for the Linear Quadratic Regulator, Journal of Operations Research Society of China, (paper)

  • M. Yang, D. Xu, Y. Li, Z. Wen, M. Chen, Sketchy Empirical Natural Gradient Methods for Deep Learning, Journal of Scientific Computing (paper)

  • M. Yang, D. Xu, H. Chen, Z. Wen, M. Chen, Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods, CVPR 2021 (paper)

  • Z. Chen, A. Milzarek, Z. Wen, A Trust-Region Method For Nonsmooth Nonconvex Optimization, Journal of Computational Mathematics (paper)

  • M. Zhao, Y. Li, Z.Wen, A Stochastic Trust-Region Framework for Policy Optimization, Journal of Computational Mathematics (paper)

  • M. Yang, A. Milzarek, Z. Wen, T. Zhang, A Stochastic Extra-Step Quasi-Newton Method for Nonsmooth Nonconvex Optimization, Mathematical Programming (paper)

  • H. Zhang, A. Milzarek, Z. Wen, W. Yin, On the geometric analysis of a quartic-quadratic optimization problem under a spherical constraint, Mathematical Programming (paper)

  • L. Wu, X. Liu, Z. Wen, Symmetric rank-1 approximation of symmetric high-order tensors, Optimization Methods and Software

  • B. Jiang, X. Meng, Z. Wen, X. Chen, An exact penalty approach for optimization with nonnegative orthogonality constraints, Mathematical Programming (paper)

  • T. Tian, Y. Cai, X. Wu, Z. Wen, Ground states and their characterization of spin-F Bose-Einstein condensates, SIAM Journal on Scientific Computing (paper)

  • Z. Jia, Z. Wen, Y. Ye, Toward Solving 2-TBSG Efficiently, Optimization Methods and Software, (paper)

  • Y. Wang, Z. Jia, Z. Wen, The Search direction Correction makes first-order methods faster, SIAM Journal on Scientific Computing (paper)

  • Y. Li, H. Liu, Z. Wen, Y, Yuan, Low-rank Matrix Optimization Using Polynomial-filtered Subspace Extraction, SIAM Journal on Scientific Computing (paper), (code)

  • Y. Duan, M. Wang, Z. Wen, Y. Yuan, Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains, SIAM Journal on Matrix Analysis and Applications, (paper)

  • J. Hu, B. Jiang, L. Lin, Z. Wen, Y. Yuan, Structured Quasi-Newton Methods for Optimization with Orthogonality Constraints, SIAM Journal on Scientific Computing (paper)

  • A. Milzarek, X. Xiao, S. Cen, Z. Wen, M. Ulbrich, A Stochastic Semismooth Newton Method for Nonsmooth Nonconvex Optimization, SIAM Journal on Optimization, (paper)

  • J. Hu, Z. Wen, A. Milzarek, Y. Yuan, Adaptive Regularized Newton Method for Riemannian Optimization, SIAM Journal on Matrix Analysis and Applications (paper)

  • Y. Li, Z. Wen, C. Yang, Y. Yuan, A Semi-smooth Newton Method For semidefinite programs and its applications in electronic structure calculations, SIAM Journal on Scientific Computing (paper)

  • J. Zhang, H. Liu, Z. Wen, S. Zhang, A Sparse Completely Positive Relaxation of the Modularity Maximization for Community Detection, SIAM Journal on Scientific Computing (paper)

  • H. Yuan, X. Gu, R. Lai, Z. Wen, Global optimization with orthogonality constraints via stochastic diffusion, Journal of Scientific Computing (paper)

  • T. Pang, Q. Li, Z. Wen, Z. Shen, Phase retrieval, a data-driven wavelet frame based approach, Applied and Computational Harmonic Analysis (paper)

  • C. Ma, X. Liu, Z. Wen, Globally Convergent Levenberg-Marquardt Method For Phase Retrieval, IEEE Transactions on Information Theory (paper)

  • C. Chen, Z. Wen, Y. Yuan, A general two-level subspace method for nonlinear optimization, Journal of Computational Mathematics

  • X. Xiao, Y. Li, Z. Wen, L. Zhang, Semi-Smooth Second-order Type Methods for Composite Convex Programs, Journal of Scientific Computing (paper)

  • Y. Yang, B. Dong, Z. Wen, Randomized Algorithms For High Quality Treatment Planning in Volumetric Modulated Arc Therapy, Inverse Problems, (paper)

  • J. Zhang, Z. Wen, Y. Zhang, Subspace Methods With Local Refinements for Eigenvalue Computation Using Low-Rank Tensor-Train Format, Journal of Scientific Computing, (pdf)

  • J. Hu, B. Jiang, X. Liu, Z. Wen, A Note on Semidefinite Programming Relaxations For Polynomial Optimization Over a Single Sphere, Science in China, Mathematics, (pdf)

  • B. Jiang, Y. Liu, Z. Wen, L_p-norm regularization algorithms for optimization over permutation matrices, SIAM Journal on Optimization, (pdf)

  • Z. Wen, Y. Zhang, Block algorithms with augmented Rayleigh-Ritz projections for large-scale eigenpair computation, SIAM Journal on Matrix Analysis and Applications (pdf)

  • X. Wu, Z. Wen, W. Bao, A regularized Newton method for computing ground states of Bose-Einstein condensates, Journal of Scientific Computing, (pdf)

  • P. Qian, Z. Wang, Z. Wen, A Composite Risk Measure Framework for Decision Making under Uncertainty, Journal of Operations Research Society of China (pdf)

  • M, Ulbrich, Z. Wen, C. Yang, D, Klockner, Z. Lu, A proximal gradient method for ensemble density functional theory, SIAM Journal on Scientific Computing, (pdf)

  • Q. Dong, X. Liu, Z. Wen, Y. Yuan, A Parallel Line Search Subspace Correction Method for Composite Convex Optimization, Journal of Operations Research Society of China (pdf)

  • X. Liu, Z. Wen, Y. Zhang, An Efficient Gauss-Newton Algorithm for Symmetric Low-Rank Product Matrix Approximations, SIAM Journal on Optimization, (pdf)

  • X. Liu, Z. Wen, X. Wang, M. Ulbrich, Y. Yuan, On the Analysis of the Discretized Kohn-Sham Density Functional Theory, SIAM Journal on Numerical Analysis, (pdf)

  • X. Zhang, J. Zhu, Z. Wen, A. Zhou, Gradient type optimization methods for electronic structure calculations, SIAM Journal on Scientific Computing (pdf)

  • Z. Wen, C. Yang, X. Liu, and Y. Zhang, Trace-Penalty Minimization for Large-scale Eigenspace Computation, Journal of Scientific Computing, (pdf)

  • X. Liu, X. Wang, Z. Wen, Y. Yuan, On the Convergence of the Self-Consistent Field Iteration in Kohn-Sham Density Functional Theory, SIAM Journal on Matrix Analysis and Applications (pdf)

  • L. Wang, A. Singer, Z. Wen, Orientation Determination from Cryo-EM images Using Least Unsquared Deviation, SIAM Journal on Imaging Sciences (pdf)

  • Z. Wen, X. Peng, X. Liu, X. Bai and X. Sun, Asset Allocation under the Basel Accord Risk Measures (pdf)

  • Z. Wen, A. Milzarek, and M. Ulbrich, and H. Zhang, Adaptive regularized self-consistent field iteration with exact Hessian for electronic structure calculation, SIAM Journal on Scientific Computing (pdf)

  • X. Liu, Z. Wen, Y. Zhang, Limited memory block Krylov subspace optimization for computing dominant singular value decompositions, SIAM Journal on Scientific Computing (pdf) (code: “LMSVD”)

  • Z. Wen, C. Yang, X. Liu and S. Marchesini, Alternating direction methods for classical and ptychographic phase retrieval, Inverse Problems (pdf)

  • Q. Ling, Y. Xu, W. Yin, and Z. Wen, Decentralized low-rank matrix completion, ICASSP 2012 (pdf) (blog)

  • R. Lai, Z. Wen, W. Yin, X. Gu and L. Lui, Folding-free global conformal mapping for genus-0 surfaces by Harmonic energy minimization, Journal of Scientific Computing (pdf)

  • Q. Ling, W. Yin and Z. Wen, Decentralized jointly sparse signal recovery by reweighted lq minimization, IEEE Transactions on Signal Processing (pdf) (blog)

  • Y. Xu, W. Yin, Z. Wen and Y. Zhang, An alternating direction algorithm for matrix completion with nonnegative factors, Frontiers of Mathematics in China, Vol. 7, No. 2, pp. 365-384 (pdf)

  • S. Yuan, Z. Wen and Y. Zhang, Augmented Lagrangian alternating direction method for matrix separation based on low-rank factorization, Optimization Methods and Software (pdf)

  • Z. Wen and W. Yin, A feasible method for optimization with orthogonality constraints, Mathematical Programming (pdf) (code)

  • J. Laska, Z. Wen, W. Yin and R. Baraniuk, Fast and accurate signal recovery from 1-bit compressive measurements, IEEE Transactions on Signal Processing (pdf)

  • Z. Wen, W. Yin and Y. Zhang, Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm, Mathematical Programming Computation (pdf) (code: “LMaFit”)

  • Z. Wen, D. Goldfarb and W. Yin, Alternating direction augmented Lagrangian methods for semidefinite programming, Mathematical Programming Computation (pdf) (code: “SDPAD”, beta1, Sept. 2009) (code: “SDPAD”, beta2, Dec. 2012) (data)

  • Z. Wen, D. Goldfarb and K. Scheinberg, Block coordinate descent methods for semidefinite programming, Handbook on Semidefinite, Cone and Polynomial Optimization (pdf)
    Previous version: Row by row methods for semidefinite programming (with D. Goldfarb, S. Ma and K. Scheinberg)

  • Z. Wen, W. Yin, D. Goldfarb and Y. Zhang, A fast algorithm for sparse reconstruction based on shrinkage, subspace optimization and continuation, SIAM Journal on Scientific Computing, Vol 32, No. 4, pp. 1832-1857 (pdf) (code: “FPC_AS”)

  • Z. Wen and W. Yin, H. Zhang and D. Goldfarb, On the convergence of an active set method for l_1 minimization, Optimization Methods and Software (pdf)

  • D. Goldfarb, S. Ma, Z. Wen, Solving low-rank matrix completion problems efficiently, Allerton’09 Proceedings of the 47th annual Allerton conference on Communication, control, and computing

  • Z. Wen and D. Goldfarb, Line search multigrid methods for large-scale nonconvex optimization, SIAM Journal on Optimization, Vol. 20, No. 3, pp. 1478-1503 (pdf) (code)

  • D. Goldfarb, Z. Wen and W. Yin, A curvilinear search method for the p-Harmonic flow on sphere, SIAM Journal on Imaging Sciences, Vol. 2, No. 1, pp. 84-109 (pdf) (code)

  • Y. Wang, Z. Wen, Z. Nashed and Q. Sun, Direct fast method for time-limited signal reconstruction, Applied Optics, Vol. 45, No. 13, pp. 3111-3126 (pdf)

  • Z. Wen, Y. Wang, A new trust region algorithm for image restoration, Science in China Series A, Vol. 48, No. 2

  • Z. Wang, Y. Yuan, Z. Wen, A subspace trust region method for large-scale unconstrained optimization, in Y.Yuan, editor, Numerical Linear Algebra and Optimization (Science Press)

Thesis

  • Z. Wen, First-order methods for semidefinite-programming, Ph.D Thesis, Columbia University, Advisor: Prof. Donald Goldfarb, 2009 (pdf)

  • Z. Wen, Least squares and their applications, M.S. Thesis, Institute of Computational Mathematics, Chinese Academy of Sciences, Advisor: Prof. Ya-xiang Yuan, 2004 (pdf (in Chinese))