Distributed Online Composite Optimization with Delayed Feedback

Ruijie Hou, Xiuxian Li, Shangce Gao

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

Abstract

This paper focuses on distributed online composite optimization with feedback delays. Using the delayed feedback and signs of relative states, a distributed online proximal gradient algorithm is proposed and then the performance of this algorithm is evaluated by dynamic regret. Under basic assumptions, a bound on dynamic regret for each agent is established, which is consistent with the existing result in the setting without regularizers. In the end, numerical examples are presented to support the theoretical finding.

Original languageEnglish
Title of host publication14th Asian Control Conference, ASCC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages43-47
Number of pages5
ISBN (Electronic)9789887581598
StatePublished - 2024
Event14th Asian Control Conference, ASCC 2024 - Dalian, China
Duration: 2024/07/052024/07/08

Publication series

Name14th Asian Control Conference, ASCC 2024

Conference

Conference14th Asian Control Conference, ASCC 2024
Country/TerritoryChina
CityDalian
Period2024/07/052024/07/08

Keywords

  • delayed feedback
  • distributed algorithms
  • dynamic regret
  • Online composite optimization

ASJC Scopus subject areas

  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Distributed Online Composite Optimization with Delayed Feedback'. Together they form a unique fingerprint.

Cite this