Distributed zero-order algorithms for nonconvex multiagent optimization

Yujie Tang, Junshan Zhang, Na Li

Research output: Contribution to journalArticlepeer-review

Abstract

Distributed multiagent optimization finds many applications in distributed learning, control, estimation, etc. Most existing algorithms assume knowledge of first-order information of the objective and have been analyzed for convex problems. However, there are situations where the objective is nonconvex, and one can only evaluate the function values at finitely many points. In this article, we consider derivative-free distributed algorithms for nonconvex multiagent optimization, based on recent progress in zero-order optimization. We develop two algorithms for different settings, provide detailed analysis of their convergence behavior, and compare them with existing centralized zero-order algorithms and gradient-based distributed algorithms.

Original languageEnglish (US)
Article number9199106
Pages (from-to)269-281
Number of pages13
JournalIEEE Transactions on Control of Network Systems
Volume8
Issue number1
DOIs
StatePublished - Mar 2021

Keywords

  • Distributed optimization
  • nonconvex optimization
  • zero-order information

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications
  • Control and Optimization

Fingerprint Dive into the research topics of 'Distributed zero-order algorithms for nonconvex multiagent optimization'. Together they form a unique fingerprint.

Cite this