A Proximal Gradient Algorithm for Composite Consensus Optimization over Directed Graphs

  • Jinshan Zeng
  • , Tao He
  • , Shikang Ouyang
  • , Mingwen Wang
  • , Xiangyu Chang

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

Abstract

This paper proposes a decentralized algorithm for solving a consensus optimization problem defined in a directed networked multi-agent system, where the local objective functions have the smooth+nonsmooth composite form. Examples of such problems include decentralized compressed sensing and constrained quadratic programming problems, as well as many decentralized regularizatlon problems. We extend the existing algorithms PG-EXTRA and ExtraPush to a new algorithm PG-ExtraPush for composite consensus optimization over a directed network. This algorithm takes advantage of the proximity operator like in PG-EXTRA to deal with the nonsmooth term, and employs the push-sum protocol like in ExtraPush to tackle the bias introduced by the directed network. We show that PG-ExtraPush converges to an optimal solution under the boundedness assumption. In numerical experiments, with a proper step size, PG-ExtraPush performs surprisingly linear rates, and is significantly faster than Subgradient-Push, even when we hand-optimize the step sizes for the latter.

Original languageEnglish
Title of host publication2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages825-830
Number of pages6
ISBN (Print)9781538604892
DOIs
StatePublished - 24 Aug 2018
Event7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017 - Honolulu, United States
Duration: 31 Jul 20174 Aug 2017

Publication series

Name2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017

Conference

Conference7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017
Country/TerritoryUnited States
CityHonolulu
Period31/07/174/08/17

Fingerprint

Dive into the research topics of 'A Proximal Gradient Algorithm for Composite Consensus Optimization over Directed Graphs'. Together they form a unique fingerprint.

Cite this