On Globally Q-Linear Convergence of a Splitting Method for Group Lasso  

作　　者：Yun-Da Dong Hai-Bin Zhang Huan Gao 

机构地区：[1]School of Mathematics and Statistics,Zhengzhou University,Zhengzhou 450001,China [2]College of Applied Sciences,Beijing University of Technology,Beijing 100124,China [3]College of Mathematics and Computational Science,Hunan First Normal University,Changsha 410205,China

出　　处：《Journal of the Operations Research Society of China》2018年第3期445-454,共10页中国运筹学会会刊（英文）

基　　金：This research was supported by the National Natural Science Foundation of China(No.61179033);Collaborative Innovation Center on Beijing Society-Building and Social Governance.

摘　　要：In this paper,we discuss a splitting method for group Lasso.By assuming that the sequence of the step lengths has positive lower bound and positive upper bound(unrelated to the given problem data),we prove its Q-linear rate of convergence of the distance sequence of the iterates to the solution set.Moreover,we make comparisons with convergence of the proximal gradient method analyzed very recently.

关 键 词：Group Lasso Splitting method Proximal gradient method Q-linear rate of convergence 

分 类 号：O17[理学—数学]