Stopping rules for accelerated gradient methods with additive noise in gradient

dc.bibliographicCitation.seriesTitleWIAS Preprintseng
dc.bibliographicCitation.volume2812
dc.contributor.authorVasin, Artem
dc.contributor.authorGasnikov, Alexander
dc.contributor.authorSpokoiny, Vladimir
dc.date.accessioned2022-07-05T14:00:01Z
dc.date.available2022-07-05T14:00:01Z
dc.date.issued2021
dc.description.abstractIn this article, we investigate an accelerated first-order method, namely, the method of similar triangles, which is optimal in the class of convex (strongly convex) problems with a Lipschitz gradient. The paper considers a model of additive noise in a gradient and a Euclidean prox- structure for not necessarily bounded sets. Convergence estimates are obtained in the case of strong convexity and its absence, and a stopping criterion is proposed for not strongly convex problems.eng
dc.description.versionpublishedVersioneng
dc.identifier.urihttps://oa.tib.eu/renate/handle/123456789/9530
dc.identifier.urihttps://doi.org/10.34657/8568
dc.language.isoeng
dc.publisherBerlin : Weierstraß-Institut für Angewandte Analysis und Stochastik
dc.relation.doihttps://doi.org/10.20347/WIAS.PREPRINT.2812
dc.relation.issn2198-5855
dc.rights.licenseThis document may be downloaded, read, stored and printed for your own use within the limits of § 53 UrhG but it may not be distributed via the internet or passed on to external parties.eng
dc.rights.licenseDieses Dokument darf im Rahmen von § 53 UrhG zum eigenen Gebrauch kostenfrei heruntergeladen, gelesen, gespeichert und ausgedruckt, aber nicht im Internet bereitgestellt oder an Außenstehende weitergegeben werden.ger
dc.subject.ddc510
dc.subject.otherAccelerated methodseng
dc.subject.otherinexact gradienteng
dc.subject.otherstopping ruleeng
dc.subject.otherinverse problemseng
dc.titleStopping rules for accelerated gradient methods with additive noise in gradienteng
dc.typeReporteng
dc.typeTexteng
dcterms.extent38 S.
tib.accessRightsopenAccess
wgl.contributorWIAS
wgl.subjectMathematik
wgl.typeReport / Forschungsbericht / Arbeitspapier
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
wias_preprints_2812.pdf
Size:
1.11 MB
Format:
Adobe Portable Document Format
Description: