Distributed Subgradient Algorithm Over Non-Independent Randomly Time-Varying Graphs

  • Yan Chen*
  • , Alexander L. Fradkov
  • , Keli Fu
  • , Xiaozheng Fu
  • , Tao Li
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We investigate the distributed stochastic optimization by nodes over the uncertain communication topologies to cooperatively minimize a sum of strongly convex local cost functions. The communication topologies are described by a sequence of time-varying stochastic directed graphs, in which every node and edge corresponds to a local optimizer and a link. We prove that if the subgradients of the local cost functions are Lipschitz continuous and the sequence of directed graphs is conditionally balanced and uniformly conditionally jointly connected, then by properly choosing the algorithm step sizes, the convergence of all nodes’ states to the global optimal solution is achieved almost surely and in mean square.

Original languageEnglish
Title of host publicationProceedings of the 8th International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’24)
EditorsSergey Kovalev, Andrey Sukhanov, Igor Kotenko, Yin Li, Yao Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages127-136
Number of pages10
ISBN (Print)9783031774102
DOIs
StatePublished - 2024
Event8th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2024 - Harbin, China
Duration: 1 Nov 20247 Nov 2024

Publication series

NameLecture Notes in Networks and Systems
Volume1210 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference8th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2024
Country/TerritoryChina
CityHarbin
Period1/11/247/11/24

Keywords

  • Distributed subgradient optimization
  • Non-independent random time-varying graphs

Fingerprint

Dive into the research topics of 'Distributed Subgradient Algorithm Over Non-Independent Randomly Time-Varying Graphs'. Together they form a unique fingerprint.

Cite this