中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 数学与系统科学研究院
  3. 中国科学院数学与系统科学研究院
  4. 计算数学与科学工程计算研究所
Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights

文献类型：期刊论文

作者Chen, Caihua1; Li, Min1; Liu, Xin2,3; Ye, Yinyu1,4
刊名MATHEMATICAL PROGRAMMING
出版日期2019
卷号173期号:1-2页码:37-77
关键词Nonseparable convex minimization Alternating direction method of multipliers Block coordinate descent method Iterate convergence Random permutation
ISSN号0025-5610
DOI10.1007/s10107-017-1205-9
英文摘要In this paper, we establish the convergence of the proximal alternating direction method of multipliers (ADMM) and block coordinate descent (BCD) method for nonseparable minimization models with quadratic coupling terms. The novel convergence results presented in this paper answer several open questions that have been the subject of considerable discussion. We firstly extend the 2-block proximal ADMM to linearly constrained convex optimization with a coupled quadratic objective function, an area where theoretical understanding is currently lacking, and prove that the sequence generated by the proximal ADMM converges in point-wise manner to a primal-dual solution pair. Moreover, we apply randomly permuted ADMM (RPADMM) to nonseparable multi-block convex optimization, and prove its expected convergence for a class of nonseparable quadratic programming problems. When the linear constraint vanishes, the 2-block proximal ADMM and RPADMM reduce to the 2-block cyclic proximal BCD method and randomly permuted BCD (RPBCD). Our study provides the first iterate convergence result for 2-block cyclic proximal BCD without assuming the boundedness of the iterates. We also theoretically establish the expected iterate convergence result concerning multi-block RPBCD for convex quadratic optimization. In addition, we demonstrate that RPBCD may have a worse convergence rate than cyclic proximal BCD for 2-block convex quadratic minimization problems. Although the results on RPADMM and RPBCD are restricted to quadratic minimization models, they provide some interesting insights: (1) random permutation makes ADMM and BCD more robust for multi-block convex minimization problems; (2) cyclic BCD may outperform RPBCD for nice problems, and RPBCD should be applied with caution when solving general convex optimization problems especially with a few blocks.
资助项目National Natural Science Foundation of China[11401300] ; National Natural Science Foundation of China[71732003] ; National Natural Science Foundation of China[71673130] ; National Natural Science Foundation of China[11771078] ; National Natural Science Foundation of China[71390335] ; National Natural Science Foundation of China[71661147004] ; National Natural Science Foundation of China[11622112] ; National Natural Science Foundation of China[11471325] ; National Natural Science Foundation of China[91530204] ; National Natural Science Foundation of China[11331012] ; National Natural Science Foundation of China[11461161005] ; National Natural Science Foundation of China[11688101] ; National Center for Mathematics and Interdisciplinary Sciences, CAS ; Youth Innovation Promotion Association, CAS ; Key Research Program of Frontier Sciences, CAS ; AFOSR Grant[FA9550-12-1-0396]
WOS研究方向Computer Science ; Operations Research & Management Science ; Mathematics
语种英语
WOS记录号WOS:000456970900002
出版者SPRINGER HEIDELBERG
源URL[http://ir.amss.ac.cn/handle/2S8OKBNM/32388]  
专题计算数学与科学工程计算研究所
通讯作者Liu, Xin
作者单位1.Nanjing Univ, Sch Management & Engn, Int Ctr Management Sci & Engn, Nanjing, Jiangsu, Peoples R China
2.Chinese Acad Sci, Acad Math & Syst Sci, State Key Lab Sci & Engn Comp, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Sch Math Sci, Beijing, Peoples R China
4.Stanford Univ, Sch Engn, Dept Management Sci & Engn, Stanford, CA 94305 USA
推荐引用方式
GB/T 7714		 Chen, Caihua,Li, Min,Liu, Xin,et al. Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights[J]. MATHEMATICAL PROGRAMMING,2019,173(1-2):37-77.
APA Chen, Caihua,Li, Min,Liu, Xin,&Ye, Yinyu.(2019).Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights.MATHEMATICAL PROGRAMMING,173(1-2),37-77.
MLA Chen, Caihua,et al."Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights".MATHEMATICAL PROGRAMMING 173.1-2(2019):37-77.

入库方式： OAI收割

来源：数学与系统科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。