报告标题:Exact continuous relaxations and algorithms for regularized optimization problems
报告人:边伟 教授(哈尔滨工业大学)
报告时间:2023年3月31日(星期五) 16:00—17:00
报告地点:(腾讯会议)会议号:149-707-913 会议密码:123456
邀请人:王洪博士
摘要:In this talk, we consider two classes of regularized optimization problems, in which the group sparsity is considered. Firstly, we give the continuous relaxation models of the considered problem and establish the equivalence of these two problems in the sense of global minimizers. Then, we define a class of stationary points of the relaxation problem, and prove that any defined stationary point is a local minimizer of the considered regularized problem and satisfies a desirable property of its global minimizers. Further, based on the difference-of-convex (DC) structure of the relaxation problem, we design some corresponding algorithms and prove their convergence properties. Finally, some numerical experiments are illustrated to show the efficiency of the proposed algorithms.
报告人简介:边伟,哈尔滨工业大学数学学院,教授、博士生导师。2004年和2009年于哈尔滨工业大学分别获得学士和博士学位,随后入职哈工大数学学院。2010-2012年访问香港理工大学跟随陈小君教授,从事博士后工作。主要从事的研究领域为:最优化理论与算法、神经网络。先后在 MP, SIOPT, SIIMS, SINUA,SISC, MOR和多个IEEE系列汇刊发表多篇学术论文。先后主持3项国家自然科学基金项目,并获得2018年度 “龙江青年学者”和2019年度国家级青年人才。现任中国运筹学会理事,中国运筹学会数学规划分会理事,黑龙江数学会常务理事,国际期刊JOTA编委。