Processing math: 0%
alt text 

Jingwang Li

PhD Student
Department of Electronic & Computer Engineering
The Hong Kong University of Science & Technology

Email: jingwang.li [at] connect.ust.hk
Google Scholar | Github

About

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.

News

Research Interests

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.

Publications

* indicates the corresponding author.

Preprints

  1. Jingwang Li and Housheng Su*. “Decentralized constraint-coupled optimization with inexact oracle”, arXiv:2309.06330, 2023. [arXiv]

  2. Jingwang Li and Housheng Su*. “Gradient tracking: A unified approach to smooth distributed optimization”, arXiv:2202.09804, 2022. [arXiv]

Journal Articles

  1. 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]

  2. 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]

  3. Jingwang Li and Housheng Su*. “Implicit tracking-based distributed constraint-coupled optimization”, IEEE Transactions on Control of Network Systems, 2022. [DOI] [arXiv]

Conference Proceedings

  1. 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]

  2. 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]

Academic Services

Reviewer for

Awards & Honors

Visitors Map