Accelerated Gossip via Stochastic Heavy Ball Method

Nicolas Loizou, Peter Richtarik

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

4 Scopus citations

Abstract

In this paper we show how the stochastic heavy ball method (SHB)-a popular method for solving stochastic convex and non-convex optimization problems-operates as a randomized gossip algorithm. In particular, we focus on two special cases of SHB: the Randomized Kaczmarz method with momentum and its block variant. Building upon a recent framework for the design and analysis of randomized gossip algorithms [20] we interpret the distributed nature of the proposed methods. We present novel protocols for solving the average consensus problem where in each step all nodes of the network update their values but only a subset of them exchange their private values. Numerical experiments on popular wireless sensor networks showing the benefits of our protocols are also presented.
Original languageEnglish (US)
Title of host publication2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages927-934
Number of pages8
ISBN (Print)9781538665961
DOIs
StatePublished - Mar 1 2019

Fingerprint Dive into the research topics of 'Accelerated Gossip via Stochastic Heavy Ball Method'. Together they form a unique fingerprint.

Cite this