期刊
APPLIED INTELLIGENCE
卷 52, 期 12, 页码 14233-14245出版社
SPRINGER
DOI: 10.1007/s10489-022-03319-4
关键词
Alternating direction method of multipliers; Convex composite optimization; Stochastic approximation; Variance reduction
资金
- Project of National Natural Science Foundation of China [11731013, 11991022]
- Project of Promoting Scientific Research Ability of Excellent Young Teachers - University of Chinese Academy of Sciences
This paper introduces a faster stochastic alternating direction method for solving large scale convex composite problems, incorporating a randomization scheme to reduce computational time. The method is shown to be effective in numerical experiments and has unified the stochastic ADMM for solving general convex and strongly convex composite problems.
Inspired by the fact that certain randomization schemes incorporated into the stochastic (proximal) gradient methods allow for a large reduction in computational time, we incorporate such a scheme into stochastic alternating direction method of multipliers (ADMM), yielding a faster stochastic alternating direction method (FSADM) for solving a class of large scale convex composite problems. In the numerical experiments, we observe a reduction of this method in computational time compared to previous methods. More importantly, we unify the stochastic ADMM for solving general convex and strongly convex composite problems (i.e., the iterative scheme does not change when the the problem goes from strongly convex to general convex). In addition, we establish the convergence rates of FSADM for these two cases.
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