Academic Activities

Current position: Home Academic Activities Content
Liyuan Scholars Colloquium Session 156:Variance-reduced first-order methods for constrained stochastic and finite-sum optimization

Time:2025-12-05 11:35

主讲人 Zhaosong Lü 讲座时间 16:30–17:30, December 11, 2025
讲座地点 Room 2, Huixing Building, Yuehai Campus, Shenzhen University 实际会议时间日 11
实际会议时间年月 2025.12

Shenzhen University School of Mathematical Sciences  

Liyuan Scholars Colloquium Session 156  


Title: Variance-reduced first-order methods for constrained stochastic and finite-sum optimization

Speaker: Professor Zhaosong Lü (University of Minnesota System)  

Time: 16:30–17:30, December 11, 2025

Location: Room 2, Huixing Building, Yuehai Campus, Shenzhen University

Abstract:  We consider stochastic and finite-sum optimization problems with deterministic constraints. Existing methods typically focus on finding an approximate stochastic solution that ensures the expected constraint violations and optimality conditions meet a prescribed accuracy. However, such an approximate solution can possibly lead to significant constraint violations. To address this issue, we propose variance-reduced first-order methods that treat the objective and constraints differently. Under suitable assumptions, our proposed methods achieve stronger approximate stochastic solutions with complexity guarantees that more reliably satisfy the constraints compared to existing methods. This is joint work with Sanyou Mei (HKUST) and Yifeng Xiao (UMN).

Speaker Profile:  Professor Zhaosong Lü currently serves as a professor in the Department of Industrial and Systems Engineering at the University of Minnesota. He earned his Ph.D. in Operations Research from the Georgia Institute of Technology. His research focuses on the theory and algorithm design of continuous optimization, with findings widely applied in data science and machine learning.

Professor Lü has published numerous high-impact research papers in leading journals such as Mathematical Programming, Mathematics of Operations Research, and SIAM Journal on Optimization. His work has received funding support from U.S. agencies including AFOSR, NSF, and ONR. He has served on the judging panels for several prestigious academic awards, including the INFORMS George Nicholson Prize and the ICCOPT Best Paper Award. He is also actively engaged in scholarly service, having served as Associate Editor for international journals such as SIAM Journal on Optimization, Computational Optimization and Applications, and Journal of Global Optimization.


All faculty and students are welcome!  


School of Mathematical Sciences  

December 5, 2025