Semi-cyclic stochastic gradient descent

Hubert Eichner*, Tomer Koren, H. Brendan McMahan, Nathan Srebro, Kunal Talwar

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

25 Scopus citations

Abstract

We consider convex SGD updates with a block-cyclic structure, i.e., where each cycle consists of a small number of blocks, each with many samples from a possibly different, block-specific, distribution. This situation arises, e.g., in Federated Learning where the mobile devices available for updates at different times during the day have different characteristics. Wc show that such block-cyclic structure can significantly deteriorate the performance of SGD, but propose a simple approach that allows prediction with the same guarantees as for i.i.d., non-cyclic, sampling.

Original languageEnglish
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)
Pages3165-3177
Number of pages13
ISBN (Electronic)9781510886988
StatePublished - 2019
Externally publishedYes
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: 9 Jun 201915 Jun 2019

Publication series

Name36th International Conference on Machine Learning, ICML 2019
Volume2019-June

Conference

Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach
Period9/06/1915/06/19

Funding

FundersFunder number
NSF-BSF1718970
Google

    Fingerprint

    Dive into the research topics of 'Semi-cyclic stochastic gradient descent'. Together they form a unique fingerprint.

    Cite this