First Analysis of Local GD on Heterogeneous Data
dc.contributor.author | Khaled, Ahmed | |
dc.contributor.author | Mishchenko, Konstantin | |
dc.contributor.author | Richtarik, Peter | |
dc.date.accessioned | 2019-11-27T12:49:18Z | |
dc.date.available | 2019-11-27T12:49:18Z | |
dc.date.issued | 2019-09-10 | |
dc.identifier.uri | http://hdl.handle.net/10754/660287 | |
dc.description.abstract | We 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.publisher | arXiv | |
dc.relation.url | https://arxiv.org/pdf/1909.04715 | |
dc.rights | Archived with thanks to arXiv | |
dc.title | First Analysis of Local GD on Heterogeneous Data | |
dc.type | Preprint | |
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 | Cairo University | |
dc.identifier.arxivid | 1909.04715 | |
kaust.person | Mishchenko, Konstantin | |
kaust.person | Richtarik, Peter | |
refterms.dateFOA | 2019-11-27T12:49:35Z |
Files in this item
This item appears in the following Collection(s)
-
Preprints
-
Computer Science Program
For more information visit: https://cemse.kaust.edu.sa/cs -
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
For more information visit: https://cemse.kaust.edu.sa/