版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:Univ Fed Goias Inst Math & Stat Campus 2Caixa Postal 131 BR-74001970 Goiania Go Brazil Georgia Inst Technol Sch Ind & Syst Engn Atlanta GA 30332 USA
出 版 物:《SIAM JOURNAL ON OPTIMIZATION》 (工业与应用数学会最优化杂志)
年 卷 期:2017年第27卷第1期
页 面:379-407页
核心收录:
学科分类:07[理学] 070104[理学-应用数学] 0701[理学-数学]
基 金:CNPq [406250/2013-8, 444134/2014-0, 309370/2014-0, 200852/2014-0, 201047/2014-4] FAPEG/GO NSF [CMMI-1300221.] Directorate For Engineering Div Of Civil, Mechanical, & Manufact Inn Funding Source: National Science Foundation
主 题:alternating direction method of multipliers hybrid proximal extragradient method non-Euclidean Bregman distances convex program pointwise iteration-complexity first-order methods inexact proximal point method regularization
摘 要:This paper describes a regularized variant of the alternating direction method of multipliers (ADMM) for solving linearly constrained convex programs. It is shown that the pointwise iteration-complexity of the new variant is better than the corresponding one for the standard ADMM method and that, up to a logarithmic term, is identical to the ergodic iteration-complexity of the latter method. Our analysis is based on first presenting and establishing the pointwise iteration-complexity of a regularized non-Euclidean hybrid proximal extragradient framework whose error condition at each iteration includes both a relative error and a summable error. It is then shown that the new ADMM variant is a special instance of the latter framework where the sequence of summable errors is identically zero when the ADMM stepsize is less than one or a nontrivial sequence when the stepsize is in the interval [1, (1 + root 5)/2).