![]() |
Jingwang Li
PhD Student Email: jingwang.li [at] connect.ust.hk |
I am currently a PhD student at the Hong Kong University of Science & Technology, under the supervision of Prof. Vincent Lau.
Previously, I earned a BMgmt in Engineering Management from Huazhong Agricultural University, and an MEng in Control Science & Engineering from Huazhong University of Science & Technology, supervised by Prof. Housheng Su. Following this, I worked as an algorithm engineer at FABU.AI, focusing on modeling and solving optimization problems related to autonomous driving. Upon deciding to pursue a PhD, I moved to the Chinese University of Hong Kong, Shenzhen as a research assistant, mentored by Prof. Xiao Li.
For further details, please refer to my CV.
Aug. 2024: I start my PhD at HKUST.
My research interests primarily lie in algorithm design and convergence analysis for decentralized optimization. Currently, I am particularly focused on a class of decentralized optimization problems with globally coupled constraints, formulated as:
min
where f_i:\mathbb{R}^{d_i} \rightarrow \mathbb{R} is a convex and smooth function, g_i:\mathbb{R}^{d_i} \rightarrow \mathbb{R} \cup \{+\infty\} and h:\mathbb{R}^p \rightarrow \mathbb{R} \cup \{+\infty\} are convex but possibly nonsmooth functions, and A_i \in \mathbb{R}^{p \times d_i} is a matrix, i = 1, \cdots, n. In the decentralized setting, we are required to solve \eqref{original_pro} over a networked system of n agents, where the network topology is represented by an undirected or directed graph. Notably, f_i, g_i, and A_i are private to agent i, while h is public for all agents. This formulation captures a broad spectrum of real-world applications, including decentralized control, vertical federated learning, and resource allocation.
* indicates the corresponding author.
Jingwang Li and Housheng Su*. “Decentralized constraint-coupled optimization with inexact oracle”, arXiv:2309.06330, 2023. [arXiv]
Jingwang Li and Housheng Su*. “Gradient tracking: A unified approach to smooth distributed optimization”, arXiv:2202.09804, 2022. [arXiv]
Jingwang Li and Housheng Su*. “NPGA: A unified algorithmic framework for decentralized constraint-coupled optimization”, IEEE Transactions on Control of Network Systems, 2024. [DOI] [arXiv]
Jingwang Li, Qing An and Housheng Su*. “Proximal nested primal-dual gradient algorithms for distributed constraint-coupled composite optimization”, Applied Mathematics and Computation, 2023. [DOI]
Jingwang Li and Housheng Su*. “Implicit tracking-based distributed constraint-coupled optimization”, IEEE Transactions on Control of Network Systems, 2022. [DOI] [arXiv]
Bingxi Jia*, Haidong Ren, Zheng Yang, Jingwang Li and Xiaofei He. “Cascaded motion estimation for intelligent vehicles in GNSS-denied scenes”, Chinese Control Conference, 2023. [DOI]
Jingwang Li, Suoxia Miao and Housheng Su*. “Distributed primal-dual mirror dynamics for constraint-coupled optimization”, International Conference on Guidance, Navigation and Control, 2022. [DOI]
Reviewer for
IEEE Transactions on Control of Network Systems
IEEE Transactions on Network Science and Engineering
IEEE Transactions on Systems, Man and Cybernetics: Systems
Journal of Computational and Applied Mathematics
Jun. 2022: Outstanding Graduate of Huazhong University of Science & Technology [PDF]
Sept. 2019: First Prize in the National Innovation Contest for Intelligent Construction and Management [PDF]
Sept. 2019: Outstanding Bachelor's Thesis Award of Huazhong Agricultural University [PDF]
Jun. 2019: Outstanding Graduate of Huazhong Agricultural University [PDF]
Nov. 2017: First Prize in the China Undergraduate Mathematical Contest in Modeling [PDF]