期刊
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS
卷 179, 期 2, 页码 676-695出版社
SPRINGER/PLENUM PUBLISHERS
DOI: 10.1007/s10957-018-1270-0
关键词
Stochastic ADMM; Duality gap; Variance estimation; Importance sampling; 90C06; 90C25; 90C30
资金
- National Science Foundation [DMS 1719932]
In this paper, we incorporate importance sampling strategy into accelerated framework of stochastic alternating direction method of multipliers for solving a class of stochastic composite problems with linear equality constraint. The rates of convergence for primal residual and feasibility violation are established. Moreover, the estimation of variance of stochastic gradient is improved due to the use of important sampling. The proposed algorithm is capable of dealing with the situation, where the feasible set is unbounded. The experimental results indicate the effectiveness of the proposed method.
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。
推荐
暂无数据