数学优化及其应用系列报告
A stochastic linearized proximal method of multipliers for convex stochastic optimization with expectation constraints
报告专家: 张立卫 教授 (大连理工大学数学科学学院)
邀请人:陈亮
时间:2022年5月19日 (星期四) 8:00-9:00 AM
报告形式:在线报告(腾讯会议)
腾讯会议号:180 948 585
入会链接:https://meeting.tencent.com/dm/9MujBL1JbFOd
报告摘要
This talk considers the problem of minimizing a convex expectation function with a set of inequality convex ex-
pectation constraints. We present a computable stochastic approximation type algorithm, namely the stochastic
linearized proximal method of multipliers, to solve this convex stochastic optimization problem. This algorithm
can be roughly viewed as a hybrid of stochastic approximation and the traditional proximal method of multipli-
ers. Under mild conditions, we show that this algorithm exhibits O(K−1/2) expected convergence rates for both
objective reduction and constraint violation if parameters in the algorithm are properly chosen, where K denotes
the number of iterations. Moreover, we show that, with high probability, the algorithm has O(log(K)K−1/2) con-
straint violation bound and O(log(K)3/2K−1/2) objective bound. Some preliminary numerical results demonstrate
the performance of the proposed algorithm.
专家简介
张立卫教授,大连理工大学数学科学学院运筹学与控制论业博士生指导教师,金融数学与保险精算专业博士生指导教师。
他于1989年,1992年,1998年分别在大连理工大学获得理学学士,硕士,博士学位,1999-2001在中科院计算数学所从事博士后工作。 目前的
研究兴趣是“矩阵优化”,“随机规划”与“均衡优化”。
他完成和主持自然科学基金面上基金多项,重点基金子课题两项。 在国际顶级期刊 Math. Programming, Operations Research, SIAM J.
Optimization, Mathematics of Operations Research, Mathematics of Computa-tion 发表论文10余篇,2020年获得中国运筹学会运筹研究奖,
现任中国运筹学会常务理事,中国运筹学会数学规划分会副理事长,中国运筹学会金融工程与金融风险管理分会副理事长,《JAPOR》和《运筹学
学报》编委。