Stochastic Primal-Dual Coordinate Method with Large Step Size for Composite Optimization with Composite Cone-constraints
Optimization and Control
2019-05-06 v1
Abstract
We introduce a stochastic coordinate extension of the first-order primal-dual method studied by Cohen and Zhu (1984) and Zhao and Zhu (2018) to solve Composite Optimization with Composite Cone-constraints (COCC). In this method, we randomly choose a block of variables based on the uniform distribution. The linearization and Bregman-like function (core function) to that randomly selected block allow us to get simple parallel primal-dual decomposition for COCC. We obtain almost surely convergence and O(1/t) expected convergence rate in this work. The high probability complexity bound is also derived in this paper.
Cite
@article{arxiv.1905.01020,
title = {Stochastic Primal-Dual Coordinate Method with Large Step Size for Composite Optimization with Composite Cone-constraints},
author = {Daoli Zhu and Lei Zhao},
journal= {arXiv preprint arXiv:1905.01020},
year = {2019}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1804.00801