On primal and dual approaches for distributed stochastic convex optimization over networks
dc.bibliographicCitation.seriesTitle | WIAS Preprints | eng |
dc.bibliographicCitation.volume | 2690 | |
dc.contributor.author | Dvinskikh, Darina | |
dc.contributor.author | Gorbunov, Eduard | |
dc.contributor.author | Gasnikov, Alexander | |
dc.contributor.author | Dvurechensky, Alexander | |
dc.contributor.author | Uribe, César A. | |
dc.date.accessioned | 2022-06-30T12:42:34Z | |
dc.date.available | 2022-06-30T12:42:34Z | |
dc.date.issued | 2020 | |
dc.description.abstract | We introduce a primal-dual stochastic gradient oracle method for distributed convex optimization problems over networks. We show that the proposed method is optimal in terms of communication steps. Additionally, we propose a new analysis method for the rate of convergence in terms of duality gap and probability of large deviations. This analysis is based on a new technique that allows to bound the distance between the iteration sequence and the optimal point. By the proper choice of batch size, we can guarantee that this distance equals (up to a constant) to the distance between the starting point and the solution. | eng |
dc.description.version | publishedVersion | eng |
dc.identifier.uri | https://oa.tib.eu/renate/handle/123456789/9340 | |
dc.identifier.uri | https://doi.org/10.34657/8378 | |
dc.language.iso | eng | |
dc.publisher | Berlin : Weierstraß-Institut für Angewandte Analysis und Stochastik | |
dc.relation.doi | https://doi.org/10.20347/WIAS.PREPRINT.2690 | |
dc.relation.hasversion | https://doi.org/10.1109/CDC40024.2019.9029798 | |
dc.relation.issn | 2198-5855 | |
dc.rights.license | This 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.license | Dieses 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.ddc | 510 | |
dc.subject.other | Convex and non-convex optimization | eng |
dc.subject.other | stochastic optimization | eng |
dc.subject.other | first-order method | eng |
dc.subject.other | adaptive method | eng |
dc.subject.other | gradient descent | eng |
dc.subject.other | complexity bounds | eng |
dc.subject.other | mini-batch | eng |
dc.title | On primal and dual approaches for distributed stochastic convex optimization over networks | eng |
dc.type | Report | eng |
dc.type | Text | eng |
dcterms.extent | 27 S. | |
tib.accessRights | openAccess | |
wgl.contributor | WIAS | |
wgl.subject | Mathematik | |
wgl.type | Report / Forschungsbericht / Arbeitspapier |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- wias_preprints_2690.pdf
- Size:
- 368.75 KB
- Format:
- Adobe Portable Document Format
- Description: