An approach to distributed parametric learning with streaming data

Ji Liu, Yang Liu, Angelia Nedich, Tamer Başar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

This paper presents an approach to solve a class of distributed parametric learning problems in a multi-agent network. Each agent acquires its private streaming data to establish a local learning model. The goal is for each agent to converge to a common global learning model, defined as the average of all local ones, by communicating only with its neighbors. Neighbor relationships are described by a time-dependent undirected graph whose vertices correspond to agents and whose edges depict neighbor relationships. It is shown that for any sequence of repeatedly jointly connected graphs, the approach leads all agents to asymptotically converge to the common global learning model, and the worst-case convergence rate is determined by the speed of local learning. A distributed linear regression problem and a distributed belief averaging problem are presented as illustrative examples.

Original languageEnglish (US)
Title of host publication2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3206-3211
Number of pages6
ISBN (Electronic)9781509028733
DOIs
StatePublished - Jun 28 2017
Event56th IEEE Annual Conference on Decision and Control, CDC 2017 - Melbourne, Australia
Duration: Dec 12 2017Dec 15 2017

Publication series

Name2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
Volume2018-January

Other

Other56th IEEE Annual Conference on Decision and Control, CDC 2017
Country/TerritoryAustralia
CityMelbourne
Period12/12/1712/15/17

ASJC Scopus subject areas

  • Decision Sciences (miscellaneous)
  • Industrial and Manufacturing Engineering
  • Control and Optimization

Fingerprint

Dive into the research topics of 'An approach to distributed parametric learning with streaming data'. Together they form a unique fingerprint.

Cite this