期刊
MATHEMATICAL PROGRAMMING
卷 129, 期 2, 页码 163-195出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s10107-011-0472-0
关键词
Proximal algorithm; Incremental method; Gradient method; Convex
类别
资金
- AFOSR [FA9550-10-1-0412]
We consider the minimization of a sum Sigma(m)(i=1) f(i)(x) consisting of a large number of convex component functions f(i). For this problem, incremental methods consisting of gradient or subgradient iterations applied to single components have proved very effective. We propose new incremental methods, consisting of proximal iterations applied to single components, as well as combinations of gradient, subgradient, and proximal iterations. We provide a convergence and rate of convergence analysis of a variety of such methods, including some that involve randomization in the selection of components. We also discuss applications in a few contexts, including signal processing and inference/machine learning.
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