Embedded Files
Background
I received my B.Sc (2011.07) and M.Sc degrees (supervisor: Prof. Zheng-Hai Huang, 2014.07) in Applied Mathematics at Tianjin University. I started my PhD study in 2014.08 in Department of Applied Mathematics at Hong Kong Polytechnic University under supervisions of Prof. Xiaojun Chen (chief-supervisor) and Prof. Ting Kei Pong (co-supervisor). I got my Ph.D. degree in 2017.09. I was a Postdoctoral Fellow from 2017.10 to 2017.12 in Department of Applied Mathematics at Hong Kong Polytechnic University supervised by Prof. Xiaojun Chen, and was a Research Fellow from 2018.01 to 2020.07 in Institute of Operations Research and Analytics at National University of Singapore supervised by Prof. Kim-Chuan Toh, and was a Research Fellow in Department of Mathematics at National University of Singapore supervised by Prof. Kim-Chuan Toh, and was a Research Fellow from 2021.09 to 2022.07 in Department of Applied Mathematics at Hong Kong Polytechnic University supervised by Prof. Xiaojun Chen. I am now a tenure-track associate professor in School of Computer Science and Engineering at Sun Yat-sen University.
Research Interests
Broadly speaking: Algorithm design, optimization theory, and applications
Current focus:
Practical inexact methods for convex or nonconvex optimization problems in data science and machine learning
Optimization methods in computational optimal transport
Distributed optimization and federated learning
Preprints
Lei Yang, Liwei Luo, and Meixia Lin. Shadow-point enhanced inexact accelerated proximal gradient method with preserved convergence guarantees. 2025.
Lei Yang, Xiangrui Kong, Min Zhang, and Yaohua Hu. An inexact variable metric proximal gradient-subgradient algorithm for a class of fractional optimization problems. 2025.
Jiayi Zhu, Ling Liang, Lei Yang, and Kim-Chuan Toh. ripALM: A relative-type inexact proximal augmented Lagrangian method with applications to quadratically regularized optimal transport. 2024.
Yuecheng Li, Tong Wang, Chuan Chen, Jian Lou, Bin Chen, Lei Yang, and Zibin Zheng. Clients collaborate: Flexible differentially private federated learning with guaranteed improvement of utility-privacy trade-off. 2024.
Yuecheng Li, Yanming Hu, Lele Fu, Chuan Chen, Lei Yang, and Zibin Zheng. Community-aware efficient graph contrastive learning via personalized self-training. 2023.
Publications in Journals
Lei Yang, Jingjing Hu, and Kim-Chuan Toh. An inexact Bregman proximal difference-of-convex algorithm with two types of relative stopping criteria. To appear in Journal of Scientific Computing, 2025.
Lei Yang and Kim-Chuan Toh. Inexact Bregman proximal gradient method and its inertial variant with absolute and partial relative stopping criteria. To appear in Mathematics of Operations Research, 2025. [arXiv]
Tianchi Liao, Lele Fu, Lei Zhang, Lei Yang, Chuan Chen, Michael K. Ng, Huawei Huang, and Zibin Zheng. Privacy-preserving vertical federated learning with tensor decomposition for data missing features. IEEE Transactions on Information Forensics and Security, 20: 3445-3460, 2025.
Lei Yang, Ling Liang, Hong T.M. Chu, and Kim-Chuan Toh. A corrected inexact proximal augmented Lagrangian method with a relative error criterion for a class of group-quadratic regularized optimal transport problems. Journal of Scientific Computing, 99: 79, 2024. [arXiv]
Lei Yang. Proximal gradient method with extrapolation and line search for a class of nonconvex and nonsmooth problems. Journal of Optimization Theory and Applications, 200(1): 68-103, 2024. [arXiv] [codes]
Hong T. M. Chu, Ling Liang, Kim-Chuan Toh, and Lei Yang. An efficient implementable inexact entropic proximal point algorithm for a class of linear programming problems. Computational Optimization and Applications, 85(1): 107-146, 2023. [arXiv]
Lei Yang and Kim-Chuan Toh. Bregman proximal point algorithm revisited: A new inexact version and its inertial variant. SIAM Journal on Optimization, 32(3): 1523--1554, 2022. [arXiv]
Lei Yang, Xiaojun Chen, and Shuhuang Xiang. Sparse solutions of a class of constrained optimization problems. Mathematics of Operations Research, 47(3): 1932-1956, 2022. [arXiv]
Lei Yang, Jia Li, Defeng Sun, and Kim-Chuan Toh. A fast globally linearly convergent algorithm for the computation of Wasserstein barycenters. Journal of Machine Learning Research, 22(21): 1–37, 2021. [arXiv]
Lei Yang, Ting Kei Pong, and Xiaojun Chen. A non-monotone alternating updating method for a class of matrix factorization problems. SIAM Journal on Optimization, 28(4): 3402--3430, 2018. [arXiv] [codes]
Lei Yang, Ting Kei Pong, and Xiaojun Chen. Alternating direction method of multipliers for a class of nonconvex and nonsmooth problems with applications to background/foreground extraction. SIAM Journal on Imaging Sciences, 10(1): 74--110, 2017. [arXiv] [local pdf file]
Lei Yang, Zheng-Hai Huang, Shenglong Hu, and Jiye Han. An iterative algorithm for third-order tensor multi-rank minimization. Computational Optimization and Applications, 63(1): 169--202, 2016. [local pdf file]
Xian-Jun Shi, Lei Yang, and Zheng-Hai Huang. A fixed point method for the linear complementarity problem arising from American option pricing. Acta Mathematicae Applicatae Sinica, English Series, 32(4): 921--932, 2016. [local pdf file]
Min Zhang, Lei Yang, and Zheng-Hai Huang. Minimum n-rank approximation via iterative hard thresholding. Applied Mathematics and Computation, 256: 860--875, 2015. [arXiv] [local pdf file]
Lei Yang, Zheng-Hai Huang, and Yu-Fan Li. A splitting augmented Lagrangian method for low multilinear-rank tensor recovery. Asia-Pacific Journal of Operational Research, 32(1): 1540008 (25p), 2015. [arXiv] [local pdf file]
Lei Yang, Zheng-Hai Huang, and XianJun Shi. A fixed point iterative method for low n-rank tensor pursuit. IEEE Transactions on Signal Processing, 61(11): 2952--2962, 2013. [local pdf file]
Publications in Conferences
Yuecheng Li, Jialong Chen, Chuan Chen, Lei Yang, and Zibin Zheng. Contrastive deep nonnegative matrix factorization for community detection. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.
Talks
MOS2023 (Young Plenary Talk), Bregman proximal point algorithm revisited: A new inexact version and its inertial variant, Chendu, May 2023.
ICCOPT 2019, A fast globally linearly convergent algorithm for the computation of Wasserstein barycenters, Berlin, August 2019.
2018 INFORMS Annual Meeting, A fast globally linearly convergent algorithm for the computation of Wasserstein barycenters, Phoenix, November 2018.
Workshop on New Optimization Methods, A non-monotone alternating updating method for a class of matrix factorization problems, Hong Kong, November 2017.
2017 Imaging Science Camp, A non-monotone alternating updating method for a class of matrix factorization problems, Shenzhen, March 2017.
ICCOPT 2016, ADMM for a class of nonconvex and nonsmooth problems with applications to background/foreground extraction, Tokyo, August 2016.
SIAM Annual Meeting 2016 (Student Discuss Section), ADMM for a class of nonconvex and nonsmooth problems with applications to background/foreground extraction, Boston, July 2016.
HKMS Annual General Meeting 2015, Alternating direction method of multipliers for nonconvex background/foreground extraction, Hong Kong, May 2015.
SIAM-IS 2014, Minimum n-rank approximation via iterative hard thresholding, Hong Kong, May 2014.
Visits
2016.03 -- 2016.07, University of California, Davis (UCD), hosted by Prof. Michael P. Friedlander.
Links
My link on Google Scholar
Google Sites
Report abuse