Convex Relaxation Algorithm for a Structured Simultaneous Low-Rank and Sparse Recovery Problem
作者机构:Department of MathematicsSouth China University of TechnologyGuangzhou 510641China
出 版 物:《Journal of the Operations Research Society of China》 (中国运筹学会会刊(英文))
年 卷 期:2015年第3卷第3期
页 面:363-379页
核心收录:
学科分类:1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 0701[理学-数学] 070101[理学-基础数学]
主 题:Simultaneous low-rank and sparse recovery Convex relaxation Error bound
摘 要:This paper is concerned with the structured simultaneous low-rank and sparse recovery,which can be formulated as the rank and zero-norm regularized least squares problem with a hard constraint diag(■)=*** this class of NP-hard problems,we propose a convex relaxation algorithm by applying the accelerated proximal gradient method to a convex relaxation model,which is yielded by the smoothed nuclear norm and the weighted l1-norm regularized least squares problem.A theoretical guarantee is provided by establishing the error bounds of the iterates to the true solution under mild restricted strong convexity *** the best of our knowledge,this work is the first one to characterize the error bound of the iterates of the algorithm to the true ***,numerical results are reported for some random test problems and synthetic data in subspace clustering to verify the efficiency of the proposed convex relaxation algorithm.