Academic Report of School of Mathematical Sciences [2026] No. 100

(Series Report for High-Level University Construction No. 1359)

Title：Efficient Proximal Splitting Algorithms for Data-Driven Nonconvex Learning Optimization Problems and Their Applications

Speaker：Professor Wu Zhongming (Nanjing University of Information Science and Technology)

Time：10:00-11:00, Oct. 26, 2026

Location：Tencent Meeting: 840464963

Abstract: Traditional optimization methods possess favorable interpretability and generalizability, while data-driven deep learning achieves remarkable performance in feature extraction. Integrating these two paradigms has become an effective strategy for solving complex inverse and optimization problems. This talk focuses on proximal splitting algorithms for knowledge-and-data co-driven nonconvex optimization. We first design efficient algorithms by exploiting the optimization properties of deep neural networks together with classical acceleration techniques. We then establish rigorous convergence guarantees based on network analysis and nonconvex optimization theory. Finally, we validate the effectiveness of the proposed algorithms on representative applications including image reconstruction and phase retrieval.

Speaker Profile：Wu Zhongming is a professor and doctoral advisor at Nanjing University of Information Science and Technology. He completed a postdoctoral fellowship at The Chinese University of Hong Kong and served as a visiting scholar at the National University of Singapore. He was selected for the Ministry of Human Resources and Social Security’s “Xiangjiang Scholars Program,” the Jiangsu Association for Science and Technology’s “Youth Support Program,” and the Jiangsu Province “Innovation and Entrepreneurship Doctoral Program,” and received the First Youth Science and Technology Award from the Jiangsu Operations Research Society. His research focuses on optimization methods and their applications. He has published numerous academic papers in journals such as the SIAM series (SIIMS/SIMODS), the IEEE series (TPAMI/TSP/TFS/TCSS), EJOR, MCOM, and Inverse Problems, and holds four authorized national invention patents. He has led research projects including General and Young Investigator Grants from the National Natural Science Foundation of China, a General Grant from the Jiangsu Provincial Natural Science Foundation, a Young Investigator Grant from the Ministry of Education’s Humanities and Social Sciences Fund, and a General Grant from the China Postdoctoral Science Foundation. He serves as Deputy Secretary-General of the Competition Working Committee of the Chinese Operations Research Society; as a Young Council Member of the Mathematical Programming Branch and the Mathematics and Intelligence Branch; and as a Council Member and Deputy Secretary-General of the Jiangsu Operations Research Society.

Faculty and students are welcome to attend!

Invited by: Tu Kai

School of Mathematical Sciences

October 23, 2026