Show simple item record

dc.contributor.authorMutny, Mojmir
dc.contributor.authorRichtarik, Peter
dc.date.accessioned2021-07-07T07:50:48Z
dc.date.available2021-07-07T07:50:48Z
dc.date.issued2018
dc.identifier.citationRichtárik, M. M. and P. (2018). Parallel Stochastic Newton Method. Journal of Computational Mathematics, 36(3), 404–425. doi:10.4208/jcm.1708-m2017-0113
dc.identifier.issn1991-7139
dc.identifier.issn0254-9409
dc.identifier.doi10.4208/jcm.1708-m2017-0113
dc.identifier.urihttp://hdl.handle.net/10754/670054
dc.description.abstractWe propose a parallel stochastic Newton method (PSN) for minimizing unconstrained smooth convex functions. We analyze the method in the strongly convex case, and give conditions under which acceleration can be expected when compared to its serial counterpart. We show how PSN can be applied to the large quadratic function minimization in general, and empirical risk minimization problems. We demonstrate the practical efficiency of the method through numerical experiments and models of simple matrix classes.
dc.publisherGlobal Science Press
dc.relation.urlhttp://global-sci.org/intro/article_detail/jcm/12268.html
dc.relation.urlhttps://arxiv.org/pdf/1705.02005
dc.rightsArchived with thanks to JOURNAL OF COMPUTATIONAL MATHEMATICS
dc.subjectoptimization
dc.subjectparallel methods
dc.subjectNewton's method
dc.subjectstochastic algorithms
dc.titlePARALLEL STOCHASTIC NEWTON METHOD
dc.typeArticle
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.identifier.journalJOURNAL OF COMPUTATIONAL MATHEMATICS
dc.identifier.wosutWOS:000455995700006
dc.eprint.versionPre-print
dc.contributor.institutionDepartment of Informatics, ETH Z¨urich, Z¨urich, Switzerland
dc.contributor.institutionSchool of Mathematics, University of Edinburgh, Edinburgh ETH9 3FD, UK
dc.identifier.volume36
dc.identifier.issue3
dc.identifier.pages404-425
dc.identifier.arxivid1705.02005
kaust.personRichtarik, Peter
refterms.dateFOA2021-07-07T07:51:54Z


Files in this item

Thumbnail
Name:
Articlefile1.pdf
Size:
858.4Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record