4.6 Article

ON THE GLOBAL LINEAR CONVERGENCE OF THE ADMM WITH MULTIBLOCK VARIABLES

期刊

SIAM JOURNAL ON OPTIMIZATION
卷 25, 期 3, 页码 1478-1497

出版社

SIAM PUBLICATIONS
DOI: 10.1137/140971178

关键词

alternating direction method of multipliers; global linear convergence; convex optimization

资金

  1. Hong Kong Research Grants Council General Research Fund Early Career Scheme [CUHK 439513]
  2. NSF grant [CMMI-1161242]

向作者/读者索取更多资源

The alternating direction method of multipliers (ADMM) has been widely used for solving structured convex optimization problems. In particular, the ADMM can solve convex programs that minimize the sum of N convex functions whose variables are linked by some linear constraints. While the convergence of the ADMM for N = 2 was well established in the literature, it remained an open problem for a long time whether the ADMM for N >= 3 is still convergent. Recently, it was shown in [Chen et al., Math. Program. (2014), DOI 10.1007/s10107-014-0826-5.] that without additional conditions the ADMM for N >= 3 generally fails to converge. In this paper, we show that under some easily verifiable and reasonable conditions the global linear convergence of the ADMM when N >= 3 can still be ensured, which is important since the ADMM is a popular method for solving large-scale multiblock optimization models and is known to perform very well in practice even when N >= 3. Our study aims to offer an explanation for this phenomenon.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据