加入收藏夹
联系我们
关于本站
个人主页
西电导航
西安电子科技大学
    当前位置:首页>>学术讲座
Inexact proximal stochastic gradient method for empirical risk minimization
时间:2018-07-02 14:25    点击:   所属单位:计算机学院
讲座名称 Inexact proximal stochastic gradient method for empirical risk minimization
讲座时间 2018-07-04 09:00:00
讲座地点 北校区主楼四区107会议室
讲座人 张洪超副教授,美国路易斯安那州立大学数学系
讲座人介绍  Hongchao Zhang is an associate professor in the Department of Mathematics and Center for Computational & Technology (CCT) at Louisiana State University (LSU).  In recent 5 years, many research papers have published at the top optimization journals, such as Math Programming, SIAM Journal on Optimization, SIAM Journal on Numerical Analysis, SIAM Journal on Imaging, Computational Optimization and Applications, etc. Most research results have been presented at major international optimization conferences and seminars at leading universities. Dr. Zhang has won Carruth McGehee Award for Excellent Research by a Junior Faculty Member in 2016, LSU Rainmakers Emerging Scholar Award in 2014, College of Science Faculty Research Award at LSU in 2014, and LSU Alumni Association Rising Faculty Research Award in 2014.
讲座内容 We will talk about an inexact proximal stochastic gradient(IPSG) method for convex composite optimization, whose objective function is a summation of an average of a large number of smooth convex functions and a convex, but possibly nonsmooth, function. Variance reduction techniques are incorporated in the method to reduce the stochastic gradient variance. The main feature of this IPSG algorithm is to allow solving the proximal subproblems inexactly while still keeping the global convergence with desirable complexity bounds. We will talk in more detail about the convergence properties of this IPSG. Some numerical results will be also discussed.
转载请注明出处:西安电子科技大学学术信息网
如果您有学术信息或学术动态,欢迎投稿。我们将在第一时间确认并收录,投稿邮箱: meeting@xidian.edu.cn
Copyright © 2011-2018 西安电子科技大学 
开发维护:电子工程学院网络信息中心  管理员:meeting@xidian.edu.cn 站长统计: