Show simple item record

dc.contributor.authorKhaled, Ahmed
dc.contributor.authorMishchenko, Konstantin
dc.contributor.authorRichtarik, Peter
dc.date.accessioned2019-11-27T12:49:18Z
dc.date.available2019-11-27T12:49:18Z
dc.date.issued2019-09-10
dc.identifier.urihttp://hdl.handle.net/10754/660287
dc.description.abstractWe provide the first convergence analysis of local gradient descent for minimizing the average of smooth and convex but otherwise arbitrary functions. Problems of this form and local gradient descent as a solution method are of importance in federated learning, where each function is based on private data stored by a user on a mobile device, and the data of different users can be arbitrarily heterogeneous. We show that in a low accuracy regime, the method has the same communication complexity as gradient descent.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/1909.04715
dc.rightsArchived with thanks to arXiv
dc.titleFirst Analysis of Local GD on Heterogeneous Data
dc.typePreprint
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.eprint.versionPre-print
dc.contributor.institutionCairo University
dc.identifier.arxivid1909.04715
kaust.personMishchenko, Konstantin
kaust.personRichtarik, Peter
refterms.dateFOA2019-11-27T12:49:35Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
394.3Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record