Show simple item record

dc.contributor.authorAybat, NS
dc.contributor.authorFallah, A
dc.contributor.authorGürbüzbalaban, M
dc.contributor.authorOzdaglar, A
dc.date.accessioned2021-11-04T16:40:38Z
dc.date.available2021-11-04T16:40:38Z
dc.date.issued2019-12
dc.identifier.urihttps://hdl.handle.net/1721.1/137365
dc.description.abstract© 2019 Neural information processing systems foundation. All rights reserved. We study the problem of minimizing a strongly convex, smooth function when we have noisy estimates of its gradient. We propose a novel multistage accelerated algorithm that is universally optimal in the sense that it achieves the optimal rate both in the deterministic and stochastic case and operates without knowledge of noise characteristics. The algorithm consists of stages that use a stochastic version of Nesterov's method with a specific restart and parameters selected to achieve the fastest reduction in the bias-variance terms in the convergence rate bounds.en_US
dc.language.isoen
dc.relation.isversionofhttps://papers.nips.cc/paper/2019/hash/d630553e32ae21fb1a6df39c702d2c5c-Abstract.htmlen_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceNeural Information Processing Systems (NIPS)en_US
dc.titleA universally optimal multistage accelerated stochastic gradient methoden_US
dc.typeArticleen_US
dc.identifier.citationAybat, NS, Fallah, A, Gürbüzbalaban, M and Ozdaglar, A. 2019. "A universally optimal multistage accelerated stochastic gradient method." Advances in Neural Information Processing Systems, 32.
dc.relation.journalAdvances in Neural Information Processing Systemsen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2021-02-03T16:29:40Z
dspace.orderedauthorsAybat, NS; Fallah, A; Gürbüzbalaban, M; Ozdaglar, Aen_US
dspace.date.submission2021-02-03T16:29:44Z
mit.journal.volume32en_US
mit.licensePUBLISHER_POLICY
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record