Jin Zhang's broad research area is comprised of optimization and variational analysis, as well as their applications in economics, engineering and data science.
Research Areas
Optimization theories: nonsmooth analysis, variational analysis and perturbational analysis
Bilevel programming problem/Mathematical programs with equilibrium constraints and their applications in machine learning and economics
Convergence analysis of optimization methods via variational analysis
Stochastic programming and robust optimization
Professional Activities
Guest editor for Pacific Journal of Optimization, special issue on hierarchical optimization.
Regular reviewer for major journals in optimization and operational research: Mathematical Programming, SIAM Journal on Optimization, Mathematics of Operations Research, European Journal of Operational Research, Annals of Operations Research, Operational Research Letters, Optimization Letters, Set-Valued and Variational Analysis, Pacific Journal of Optimization, Mathematical Methods of Operations Research.
Local organizing member for the Conference on Advances in Nonsmooth Analysis and Applications 2019, Southern University of Science and Technology.
Local organizing member for the Conference on Advances in Optimization Theory and Applications 2020, Southern University of Science and Technology.
Local organizing member for the Conference on Advances in Optimization Theory and Applications for Young Scholars 2021, Southern University of Science and Technology.
Organizing member for the Forum on Developments and Origins of Operations Research, Variational Analysis -- Theory and Application (online courses), 2021
Research Grants
Principal Investigator: Research Grants Council of Hong Kong, ``Linear convergence of the (randomized block coordinate) proximal gradient methods via variational analysis'', 2018 - 2021. 0.3 million. (terminated due to departure)
Principal Investigator: National Natural Science Foundation of China, Young scholar fund, ``Study on large-scale bilevel programming: optimality and algorithm'', 2017 - 2019. 0.2 million. (Finished)
Principal Investigator: National Natural Science Foundation of China, General fund, "Study on linear convergence of some splitting methods via variational analysis'', 2020 - 2023. 0.5 million. (on-going)
Principal Investigator: The Science and Technology Innovation Committee of Shenzhen Municipality, General fund, "Applications of Bi-level programming in contract theory'', 2021 - 2023. 0.5 million. (Finished)
Principal Investigator: The Science and Technology Innovation Committee of Shenzhen Municipality, Excellent Young Investigator Grant, "Bi-level modelling and algorithms for meta-learning and hyperparameter learning'', 2021 - 2024. 1.8 million. (on-going)
Principal Investigator: Guangdong Basic and Applied Basic Research Foundation, Distinguished Young Investigator Grant, “Bilevel Programming: theory, method and application'', 2022 - 2025. 1 million. (on-going)
Principal Investigator: The National Science Fund of China, Excellent Young Investigator Grant, “Optimization theory and method'', 2023 - 2025. 2 million. (on-going)
Principal Investigator: Natianal Key R&D Program of China, "Research on Deep Learning Models for Multi-Modal Image Data", 2024-2028, 3.2 million. (on-going)
Research Awards
Junior Research Award from Department of Science and Technology of Guangdong Province, 2022
Junior Research Award from Operations Research Society of China (ORSC), 2020
Junior Research Award from Faculty of Science, SUSTech, 2020
Courses-taught:
MATH3205: Linear and Integer Programming, Fall 2016, Hong Kong Baptist University
MATH3427: Real Analysis, Fall 2016, Hong Kong Baptist University
MATH1006: Advanced Calculus, Spring 2018, Hong Kong Baptist University
MA210: Operations Research, Spring 2019/2020/2021/2022/2023, Southern University of Science and Technology
MA433: Optimization Theory and Method, Fall 2019/2020, Southern University of Science and Technology
MA100: Calculus, Fall 2020, Southern University of Science and Technology
MAT7083: Convex Optimization Algorithm, Fall 2021/2022/2023, Southern University of Science and Technology
Research Group:
Research Assistant Professor:
Dr. Wei Yao（2022.6 - Present）, from Wuhan University (B.Sc), Chinese University of Hong Kong (M.Phi, Ph.D)
Long-term Visitor:
Prof. Jiangxing Zhu (2021.1 - 2022.1) , from Yunnan University
Prof Qingjie Hu (2022.1 - 2023.1) , from Guilin University of Electronic Technology
Prof Miantao Chao (2022.1 - 2023.1) , from Guangxi University
Prof Peili Li (2023.7 - 2024.1), from Henan University
Postdoctorate Fellows:
Dr. Wei Yao（2020.3 - 2022.5) , from Wuhan University (B.Sc), Chinese University of Hong Kong (M.Phi, Ph.D)
Dr. Xuan Luo ( 2021.8 - 2024.6), from Huazhong University of Science and Technology (B.E), City University of Hong Kong (Ph.D)
Dr. Chunhai Hu（2022.6 - Present）, from Yunnan University (B.Sc, Ph.D)
Dr. Weihao Mao（2023.3 - Present）, from Wuhan University of Technology (B.Sc), Xiamen University (Ph.D)
Dr. Haian Yin（2023.7 - Present）, from Southeast University (B.Sc), Southern University of Science and Technology (M.Phi, Ph.D)
Ph.D Students:
Haian Yin（2019.9 - 2023.6）, from Southeast University (B.Sc), Southern University of Science and Technology (M.Phi)
Yixia Song（2021.9 - Present）, from Zhengzhou University (B.Sc), Southern University of Science and Technology (M.Phi)
Peixuan Yang (2022.9 - Present ), from Jilin University (B.Sc), Nankai University (M.Phi)
Xiaoning Bai (2023.9 - Present ), from Northeastern University (B.Sc), Beijing Institute of Technology (M.Phi)
Qichao Cao (2024.9 - ), from University of Electronic Science and Technology of China (B.Sc, Ph.D)
Lvgang Zhang (2024.9 - Present ), from Jilin University (B.Sc)
Co-Supervised Ph.D Students:
Yaoshuai Ma (Co-supervisor Prof. Xiao Wang from Pengcheng Lab, 2022.9 - Present), from Liaoning Normal University (B.Sc), Guangxi University (M.Phi)
Yixuan Zhang (Chief supervisor Prof. Xiaojun Chen from Hong Kong Polytechnic University, 2022.9 - Present), from Beijing Normal University (B.Sc)，Southern University of Science and Technology (M.Phi)
Cheng Chen (Co-supervisor Prof. Xiao Wang from Pengcheng Lab, 2024.9 - Present), from Hangzhou Dianzi University (B.Sc), Southern University of Science and Technology (M.Phi)
Chengming Yu (Beijing University of Posts and Telecommunications, 2024.9 - Present), from Dalian University of Technology (B.E), Southern University of Science and Technology (M.Phi)
Master Students:
Yixia Song（2018.9 - 2021.7）, from Zhengzhou University (B.Sc), currently Ph.D student in Southern University of Science and Technology
Chengming Yu（2019.9 - 2023.6）, from Dalian University of Technology (B.E)
Yixuan Zhang（2020.9 - 2022.7）, from Beijing Normal University (B.Sc)，currently Ph.D student in Hong Kong Polytechnic University superivsed by Prof Xiaojun Chen.
Kaiqi Sun（2021.9 - 2024.7）, from Xiangtan University (B.Sc)
Feifan Wang（2022.9 - 2024.7）, from Southern University of Science and Technology (B.Sc)
Cheng Chen（2022.9 - 2024.7）, from Hangzhou Dianzi University (B.Sc)
Zhihao Zhang (2022.9 - 2024.7 ), from Jilin University (B.Sc)
Visiting Ph.D Students:
Shangzhi Zeng（2019.9 - 2020.3, 2020.7-- 2021.9）, from the University of Hong Kong. (Currently PIMS post-doc, University of Victoria, supervised by Prof Jane Ye)
Yanyun Ding（2020.6 - 2023.6）, from Beijing University of Technology
Xiaoxiao Ma（2020.8 - 2021.8）, from University of Victoria
Tianshu Chu（2023.3 - Present）, from Beijing University of Technology
Selected publication（My co-authored works always list the authors in the alphabetical order of their names to indicate equal contributions, except the works in collaboration with mainland students due to their graduation requirements）：
C.H. Hu, W. Yao and J. Zhang, Decomposition Method for Lipschitz Stability of General Lasso-Type Problems, preprint 2024.
M.T. Chao, B. Mordukhovich, Z.J. Shi and J Zhang, Coderivative-Based Newton Methods with Wolfe Linesearch for Nonsmooth Optimization, preprint 2024.
S. Fang, Y.J. Liu, W. Yao, C.M. Yu and J Zhang, qNBO: quasi-Newton Meets Bilevel Optimization, preprint 2024.
Y.S. Ma, X. Wang, W. Yao and J. Zhang, MeFBO: A Moreau Envelope Based First-Order Stochastic Gradient Method for Nonconvex Federated Bilevel Optimization, preprint 2024.
W. Yao, H.A. Yin, S.Z. Zeng and J. Zhang, Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions, preprint 2024.
L. Guo, H.A. Yin and J Zhang, A Penalized Sequential Convex Programming Approach for Continuous Network Design Problems, preprint 2024.
R.Z. Ke, C. Ryan, W. Yao and J. Zhang, A max-min reformulation approach to nonconvex bilevel optimization, preprint 2023.
X.X. Ma, W. Yao, J.J. Ye and J. Zhang, Calm local optimality for nonconvex-nonconcave minimax problems, preprint 2023.
L Gao, J.J. Ye, H.A. Yin, S.Z. Zeng and J. Zhang, Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs, preprint 2023.
R.S. Liu, Y.H. Liu, S.Z. Zeng and J. Zhang, Augmenting Iterative Trajectory for Bilevel Optimization: Methodology, Analysis and Extensions, preprint 2023.
M. Gao, W. Ouyang, J. Zhang and J.X. Zhu, Generalized metric subregularity for generalized subsmooth multifunctions in Asplund space, preprint 2022.
D. Wang, S.Z. Zeng and J. Zhang, A modularized algorithmic framework for interface related optimization problems using characteristic functions, preprint 2022.
Y.W. Li, G.H. Lin, J. Zhang and X.D. Zhu, A novel approach for bilevel programs based on Wolfe duality, preprint 2021.
R.S. Liu, Z. Liu, W. Yao, S.Z. Zeng and J. Zhang, Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy, International Conference on Machine Learning (ICML) 2024.
T.S. Chu, D.C. Xu, W. Yao and J. Zhang, SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity, International Conference on Machine Learning (ICML) 2024.
X.M. Yang, W. Yao, H.A. Yin, S.Z. Zeng and J. Zhang, Gradient-based Algorithms for Multi-Objective Bi-Level Optimization, SCIENCE CHINA Mathematics 2024 (special issue on AI Methods for Optimization Problems)
W. Yao, C.M. Yu, S.Z. Zeng and J. Zhang, Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm, ICLR 2024 spotlight presentation (<5% out of 7262 submissions)
X.F. Wang, S.Z. Zeng, J. Zhang and J.C. Zhou, Proximal-based Methods can Guarantee Blunt Local Minimizer for Nonconvex Nonsmooth Optimization Problem, Operations Research Transactions 2023 (in Chinese)
R.S. Liu, X. Liu, S.Z. Zeng, J. Zhang and Y.X. Zhang, Hierarchical Optimization-Derived Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence 2023
R.S. Liu, X. Liu, S.Z. Zeng, J. Zhang and Y.X. Zhang, Value-Function-based Sequential Minimization for Bi-level Optimization, IEEE Transactions on Pattern Analysis and Machine Intelligence 2023
K. Bai, Y.X. Song and J. Zhang, Second-order enhanced optimality conditions and constraint qualifications, Journal of Optimization Theory and Applications 2023
M. Benko, H. Gfrerer, J.J. Ye, J. Zhang and J.C. Zhou. Second-order optimality conditions for general nonconvex optimization problems and variational analysis of disjunctive systems, SIAM Journal on Optimization 2023
G.H. Lin, Z.P. Yang, H.A. Yin and J. Zhang, Dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems, Computational Optimization and Applications 2023.
R.S. Liu, X. Liu, W. Yao, S.Z. Zeng and J. Zhang, Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity, International Conference on Machine Learning (ICML) 2023.
L. Guo, J.J. Ye and J. Zhang, Sensitivity analysis of the maximal value function with applications in nonconvex minimax programs, Mathematics of Operations Research, 2023. Available at arXiv:2303.01474
X.X. Ma, W. Yao, J.J. Ye and J. Zhang, Combined approach with second-order optimality conditions for bilevel programming problem, Journal of Convex Analysis 2023 (special issue in honor of Roger J-B Wets on his 85th birthday). Available at arXiv:2108.00179v2
J.J. Ye, X.M. Yuan, S.Z. Zeng and J. Zhang, Difference of convex algorithms for bilevel programs with applications in hyperparameter selection, Mathematical Programming 2022. Available at arXiv (2102.09006).
L Chen, Y.C. Liu, X.M. Yang and J. Zhang, Stochastic approximation methods for the two-stage stochastic linear complementarity problem, SIAM Journal on Optimization, 2022
L Gao, J.J. Ye, H.A. Yin, S.Z. Zeng and J. Zhang. Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems, International Conference on Machine Learning (ICML) 2022. Available at arXiv (2206.05976).
R.S. Liu, X. Liu, S.Z. Zeng, J. Zhang and Y.X. Zhang, Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training, International Conference on Machine Learning (ICML) 2022.
B. Mordukhovich, X.M. Yuan, S.Z. Zeng and J. Zhang, A globally convergent proximal Newton-type method in nonsmooth convex optimization, Mathematical Programming 2022. Available at arXiv:2011.08166
R.S. Liu, P. Mu, X.M. Yuan, S.Z. Zeng and J. Zhang, A generic descent aggregation framework for gradient-based bilevel optimization, IEEE Transactions on Pattern Analysis and Machine Intelligence 2022. (pdf)
R.S. Liu, L. Ma, X.M. Yuan, S.Z. Zeng and J. Zhang, Task-Oriented Convex Bilevel Optimization with Latent Feasibility, IEEE Transactions on Image Processing 2022.
J. Zhang and X.D. Zhu, Linear convergence of prox-SVRG method for separable nonsmooth convex optimization problems under bounded metric subregularity, Journal of Optimization Theory and Applications, 2022.
R.Z. Ke, W. Yao, J.J. Ye and J. Zhang, Generic property of the partial calmness condition for bilevel programming problems, SIAM Journal on Optimization, 2022 Available at arXiv (2107.14469).
R.S. Liu, Y.H. Liu, S.Z. Zeng and J. Zhang, Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond, NeurIPS Spotlight paper (< 3% out of 9122 submissions) 2021
L. Wang, H. Yin and J. Zhang, Density-based Distance Preserving Graph for Graph-based Learning, IEEE Transactions on Neural Networks and Learning Systems, 2021
R.S. Liu, P. Mu and J. Zhang, Investigating Customization strategies and convergence behaviors of task-specific ADMM, IEEE Transactions on Image Processing 2021
R.Z. Ke and J. Zhang, On the First Order Approach for Bilevel Programming: Moral Hazard Case, Operations Research Transactions 2021 (in Chinese) (pdf)
J.J. Ye, X.M. Yuan, S.Z. Zeng and J. Zhang, Variational analysis perspective on linear convergence of some first order methods for nonsmooth convex optimization problems, Set-Valued and Variational Analysis 2021 (special issue dedicated to Tyrrell Rockafellar's 85th birthday) (pdf)
R.S. Liu, X. Liu, X.M. Yuan, S.Z. Zeng and J. Zhang, A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization, International Conference on Machine Learning (ICML) 2021 (pdf)
Y.C. Liu and J. Zhang, Confidence Regions of Stochastic Variational Inequalities: Error Bound Approach, Optimization, 2020. (pdf)
Y.C. Liu, X.M. Yuan and J. Zhang, Discrete Approximation Scheme in Distributionally Robust Optimization, Numerical Mathematics: Theory, Methods and Applications, 2020 (pdf)
X.F. Wang, J.J. Ye, X.M. Yuan, S.Z. Zeng and J. Zhang, Perturbation techniques for convergence analysis of proximal gradient method and other first-order algorithms via variational analysis, Set-Valued and Variational Analysis, 2020 (pdf)
R.S. Liu, P. Mu, X.M. Yuan, S.Z. Zeng and J. Zhang, A generic first-order algorithmic framework for bi-Level programming beyond lower-level singleton, International Conference on Machine Learning (ICML) 2020, (pdf, supplementary, slides)
C. Fang, X.Y. Ma, J. Zhang and X.D. Zhu, Personality information sharing in supply chain systems for innovative products in the circular economy era, International Journal of Production Research, 2020. (pdf)
X.M. Yuan, S.Z. Zeng and J. Zhang, Discerning the linear convergence of ADMM for structured convex optimization through the lens of variational analysis, Journal of Machine Learning Research 21, (2020) 1-75. (75 pages long paper, pdf)
J.S. Chen, J.J. Ye, J. Zhang and J.C. Zhou, Exact formula for the second-order tangent set of the second-order cone complementarity set, SIAM Journal on Optimization 29, no. 4 (2019) 2986–3011. (pdf)
K. Bai, J.J. Ye and J. Zhang, Directional quasi/pseudo-normality as sufficient conditions for metric subregularity, SIAM Journal on Optimization 29, no. 4 (2019) 2625—2647. (pdf)
Y.C. Liu, X.M. Yuan, S.Z. Zeng and J. Zhang, Partial error bound conditions and the linear convergence rate of ADMM, SIAM Journal on Numerical Analysis 56, no. 4 (2018) 2095—2123. (pdf)
Y.C. Liu, H.F. Xu, S. Yang and J. Zhang, Distributionally robust equilibrium for continuous games: Nash and Stackelberg models, European Journal of Operational Research 265 no. 2 (2018) 631—643.(pdf)
Y.C. Liu, X.M. Yuan, S.Z. Zeng and J. Zhang, Primal-dual hybrid gradient method for distributionally robust optimization problem, Operational Research Letters 45 no. 6, (2017) 625—630.(pdf)
G.H. Lin, M.J. Luo, D.L. Zhang and J. Zhang, Stochastic second-order-cone complementarity problems: expected residual minimization formulation and its applications, Mathematical Programming, 165, no.1 (2017), 197-233. (pdf)
G.H. Lin, M.J. Luo and J. Zhang, Smoothing and SAA method for stochastic programming problems with non-smooth objective and constraints. Journal of Global Optimization 66, no. 3 (2016), 487--510.
L. Guo, G.H. Lin, J.J. Ye and J. Zhang, Sensitivity analysis of the value function for parametric mathematical programs with equilibrium constraints. SIAM Journal on Optimization, 24, no. 3 (2014), 1206--1237. (pdf)
J.J. Ye and J. Zhang, Enhanced Karush-Kuhn-Tucker conditions for mathematical programs with equilibrium constraints. Journal of Optimization Theory and Applications 163, no. 3 (2014), 777--794. (pdf)
L. Guo, J.J. Ye and J. Zhang, Mathematical programs with geometric constraints in Banach spaces: enhanced optimality, exact penalty, and sensitivity. SIAM Journal on Optimization, 23, no. 4, (2013), 2295--2319. (pdf)
J.J. Ye and J. Zhang, Enhanced Karush-Kuhn-Tucker condition and weaker constraint qualifications. Mathematical Programming, 139, no. 1-2 (2013), 353--381. (pdf)
Publications with mainland students supervised and co-supervised
R.S. Liu, J.X. Gao, J. Zhang, D.Y. Meng and Z.C. Lin, Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond, IEEE Transactions on Pattern Analysis and Machine Intelligence 2021
Z.P. Yang, J. Zhang, Y.L. Wang and G.H. Lin, Variance-Based Subgradient Extragradient Method for Stochastic Variational Inequality Problems, Journal of Scientific Computing, 2021
X.D. Zhu, J. Zhang, J.C. Zhou and X.M. Yang, Mathematical programs with second-order cone complementarity constraints: strong stationarity and approximation method, Journal of Optimization Theory and Applications, 2019.
P. Zhang, J. Zhang, G.H. Lin and X.M. Yang, Constraint qualifications and proper Pareto optimality conditions for multiobjective problem with equilibrium constraints, Journal of Optimization Theory and Applications, 176 no. 3 (2018) 763—782
G.X. Wang, J. Zhang, B. Zeng and G.H. Lin, Expected residual minimization formulation for a class of stochastic linear second-order cone complementarity problems, European Journal of Operational Research 265 no. 2 (2018). 437—447
S.H. Jiang, J. Zhang, C.H. Chen and G.H. Lin, Smoothing partial exact penalty splitting method for mathematical programs with equilibrium constraints, Journal of Global Optimization, (2017). DOI: 10.1007/s10898-017-0539-4
Y. Zhao, J. Zhang, X.M. Yang and G.H. Lin, Expected residual minimization formulation for a class of stochastic vector variational inequalities. Journal of Optimization Theory and Applications 175 no. 2 (2017), 545--566.
