Show simple item record

dc.contributor.authorKovalev, Dmitry
dc.contributor.authorShulgin, Egor
dc.contributor.authorRichtarik, Peter
dc.contributor.authorRogozin, Alexander
dc.contributor.authorGasnikov, Alexander
dc.date.accessioned2021-02-24T11:44:51Z
dc.date.available2021-02-24T11:44:51Z
dc.date.issued2021-02-18
dc.identifier.urihttp://hdl.handle.net/10754/667661
dc.description.abstractWe propose ADOM - an accelerated method for smooth and strongly convex decentralized optimization over time-varying networks. ADOM uses a dual oracle, i.e., we assume access to the gradient of the Fenchel conjugate of the individual loss functions. Up to a constant factor, which depends on the network structure only, its communication complexity is the same as that of accelerated Nesterov gradient method (Nesterov, 2003). To the best of our knowledge, only the algorithm of Rogozin et al. (2019) has a convergence rate with similar properties. However, their algorithm converges under the very restrictive assumption that the number of network changes can not be greater than a tiny percentage of the number of iterations. This assumption is hard to satisfy in practice, as the network topology changes usually can not be controlled. In contrast, ADOM merely requires the network to stay connected throughout time.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2102.09234.pdf
dc.rightsArchived with thanks to arXiv
dc.titleADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks
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.institutionMoscow Institute of Physics and Technology, Dolgoprudny, Russia.
dc.identifier.arxivid2102.09234
kaust.personKovalev, Dmitry
kaust.personShulgin, Egor
kaust.personRichtarik, Peter
refterms.dateFOA2021-02-24T11:53:43Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
5.202Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record