Show simple item record

dc.contributor.authorLoizou, Nicolas
dc.contributor.authorRichtarik, Peter
dc.date.accessioned2019-05-29T07:15:46Z
dc.date.available2019-05-29T07:15:46Z
dc.date.issued2018-09-23
dc.identifier.urihttp://hdl.handle.net/10754/653112
dc.description.abstractIn this paper we show how the stochastic heavy ball method (SHB) -- a popularmethod for solving stochastic convex and non-convex optimization problems--operates as a randomized gossip algorithm. In particular, we focus on twospecial cases of SHB: the Randomized Kaczmarz method with momentum and itsblock variant. Building upon a recent framework for the design and analysis ofrandomized gossip algorithms, [Loizou Richtarik, 2016] we interpret thedistributed nature of the proposed methods. We present novel protocols forsolving the average consensus problem where in each step all nodes of thenetwork update their values but only a subset of them exchange their privatevalues. Numerical experiments on popular wireless sensor networks showing thebenefits of our protocols are also presented.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/1809.08657
dc.rightsArchived with thanks to arXiv
dc.titleAccelerated Gossip via Stochastic Heavy Ball Method
dc.typePreprint
dc.contributor.departmentComputer Science
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.eprint.versionPre-print
dc.contributor.institutionSchool of Mathematics, The University of Edinburgh, Edinburgh, Scotland, UK
dc.contributor.institutionThe University of Edinburgh, United Kingdom
dc.contributor.institutionMIPT, Russia
dc.identifier.arxivid1809.08657
kaust.personRichtarik, Peter
dc.versionv1
refterms.dateFOA2019-05-29T07:15:56Z


Files in this item

Thumbnail
Name:
1809.08657.pdf
Size:
893.0Kb
Format:
PDF
Description:
Preprint

This item appears in the following Collection(s)

Show simple item record