The Mirror-Prox Sliding Method for Non-smooth decentralized saddle-point problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuruzov, Ilya, Rogozin, Alexander, Yarmoshik, Demyan, Gasnikov, Alexander
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917556717092864
author Kuruzov, Ilya
Rogozin, Alexander
Yarmoshik, Demyan
Gasnikov, Alexander
author_facet Kuruzov, Ilya
Rogozin, Alexander
Yarmoshik, Demyan
Gasnikov, Alexander
contents The saddle-point optimization problems have a lot of practical applications. This paper focuses on such non-smooth problems in decentralized case. This work contains generalization of recently proposed sliding for centralized problem. Through specific penalization method and this sliding we obtain algorithm for non-smooth decentralized saddle-point problems. Note, the proposed method approaches lower bounds both for number of communication rounds and calls of (sub-)gradient per node.
format Preprint
id arxiv_https___arxiv_org_abs_2210_06086
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle The Mirror-Prox Sliding Method for Non-smooth decentralized saddle-point problems
Kuruzov, Ilya
Rogozin, Alexander
Yarmoshik, Demyan
Gasnikov, Alexander
Optimization and Control
The saddle-point optimization problems have a lot of practical applications. This paper focuses on such non-smooth problems in decentralized case. This work contains generalization of recently proposed sliding for centralized problem. Through specific penalization method and this sliding we obtain algorithm for non-smooth decentralized saddle-point problems. Note, the proposed method approaches lower bounds both for number of communication rounds and calls of (sub-)gradient per node.
title The Mirror-Prox Sliding Method for Non-smooth decentralized saddle-point problems
topic Optimization and Control
url https://arxiv.org/abs/2210.06086