搜索
报告题目：Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency
报 告 人：戚厚铎 教授，香港理工大学
工作单位：香港理工大学数据科学及人工智能学系、应用数学系
英文工作单位：Department of Data Science and Artificial Intelligence and Department of Applied Mathematics, The Hong Kong Polytechnic University
报告摘要：We investigate variants of the Frank-Wolfe (FW) algorithm for smoothing and strongly convex optimization over polyhedral sets, with the goal of designing algorithms that achieve linear convergence while minimizing per-iteration complexity as much as possible. Starting from the simple yet fundamental unit simplex, and based on geometrically intuitive motivations, we introduce a novel oracle called Simplex Linear Minimization Oracle (SLMO), which can be implemented with the same complexity as the standard FW oracle. We then present two FW variants based on SLMO: Simplex Frank-Wolfe and the refined Simplex Frank-Wolfe (rSFW). Finally, we generalize the entire framework from the unit simplex to arbitrary polytopes. Furthermore, the refinement step in rSFW can accommodate any existing FW strategies such as the well-known away-step and pairwise-step, leading to outstanding numerical performance.
报告人简介：戚厚铎，香港理工大学数据科学及人工智能学系与应用数学系联合聘任教授，研究领域包括矩阵优化及其应用、数据科学中的嵌入方法和投资组合优化。1990年获北京大学统计学学士学位，1993年获曲阜师范大学运筹学硕士学位，1996年获中国科学院应用数学研究所运筹学与最优控制博士学位。曾任英国南安普顿大学优化学教授，2022年12月加入香港理工大学。曾获澳大利亚研究理事会伊丽莎白二世研究员基金，并担任英国艾伦·图灵研究院图灵学者。现任 Asia-Pacific Journal of Operational Research 优化领域编辑，以及 Mathematical Programming Computation、Computational Optimization and Applications、Journal of the Operations Research Society of China 等期刊编委。
报告时间：2026年9月18日（星期五）09:30–10:30
报告地点：文渊楼B119教室
主办单位：数学与统计学院
学院宣传片
