dc.contributor.author Kovalev, Dmitry dc.contributor.author Shulgin, Egor dc.contributor.author Richtarik, Peter dc.contributor.author Rogozin, Alexander dc.contributor.author Gasnikov, Alexander dc.date.accessioned 2021-02-24T11:44:51Z dc.date.available 2021-02-24T11:44:51Z dc.date.issued 2021-02-18 dc.identifier.uri http://hdl.handle.net/10754/667661 dc.description.abstract We 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.publisher arXiv dc.relation.url https://arxiv.org/pdf/2102.09234.pdf dc.rights Archived with thanks to arXiv dc.title ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks dc.type Preprint dc.contributor.department Computer Science dc.contributor.department Computer Science Program dc.contributor.department Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division dc.eprint.version Pre-print dc.contributor.institution Moscow Institute of Physics and Technology, Dolgoprudny, Russia. dc.identifier.arxivid 2102.09234 kaust.person Kovalev, Dmitry kaust.person Shulgin, Egor kaust.person Richtarik, Peter refterms.dateFOA 2021-02-24T11:53:43Z
﻿

### Files in this item

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