English

Network Independent Rates in Distributed Learning

Optimization and Control 2015-09-30 v1

Abstract

We propose a new belief update rule for Distributed Non-Bayesian learning in time-varying directed graphs, where a group of agents tries to collectively identify a hypothesis that best describes a sequence of observed data. We show that the proposed update rule, inspired by the Push-Sum algorithm, is consistent, moreover we provide an explicit characterization of its convergence rate. Our main result states that, after a transient time, all agents will concentrate their beliefs at a network independent rate. Network independent rates were not available for other consensus based distributed learning algorithms.

Keywords

Cite

@article{arxiv.1509.08574,
  title  = {Network Independent Rates in Distributed Learning},
  author = {Angelia Nedić and Alex Olshevsky and César A. Uribe},
  journal= {arXiv preprint arXiv:1509.08574},
  year   = {2015}
}

Comments

Submitted to ACC2016

R2 v1 2026-06-22T11:07:43.369Z