学术报告
Stochastic approximation methods for nonconvex constrained optimization
王晓教授
（中山大学）
报告时间：2026年3月13日星期五 14:30-15:30
报告地点：沙河主楼E806
报告摘要: Nonconvex constrained optimization is a vital research area within the optimization community, encompassing a wide range of applications across various fields. However, addressing nonconvex constrained optimization presents significant challenges due to the large-scale data and inherent uncertainties as well as potentially nonconvex functional constraints in optimization models. In this talk, I will report our recent progress on stochastic approximation methods for nonconvex constrained optimization that include established complexity bounds and/or convergence properties.
报告人简介：王晓，中山大学教授、博士生导师。研究方向为大规模非凸优化算法和理论。部分成果发表在SIAM J. Optim.、SIAM J. Numer. Anal.、SIAM J. Imaging Sci.、SIAM J. Matrix. Ana. Appl.、Math. Oper. Res.、Math. Comp.、J. Mach. Learn. Res.等期刊。入选国家级青年人才计划。曾荣获中国工业与应用数学学会应用数学青年科技奖、中国运筹学会青年科技奖。目前担任中国运筹学会理事、广东省运筹学会副理事长、中国工业与应用数学学会优化及其应用专委会（筹）秘书长。
邀请人：韩德仁，崔春风
