Show simple item record

dc.contributor.authorOdeyomi, Olusola T.
dc.contributor.authorZáruba, Gergely V.
dc.date.accessioned2021-10-18T02:17:19Z
dc.date.available2021-10-18T02:17:19Z
dc.date.issued2021-07-12
dc.identifier.citationOdeyomi, O., & Zaruba, G. (2021). Differentially-private federated learning with long-term constraints using online mirror descent. Paper presented at the IEEE International Symposium on Information Theory - Proceedings, , 2021-July 1308-1313. doi:10.1109/ISIT45174.2021.9518177en_US
dc.identifier.isbn978-1-5386-8209-8
dc.identifier.isbn978-1-5386-8210-4
dc.identifier.urihttps://doi.org/10.1109/ISIT45174.2021.9518177
dc.identifier.urihttps://soar.wichita.edu/handle/10057/22209
dc.descriptionClick on the DOI link to access this conference paper at the publishers website (may not be free).en_US
dc.description.abstractThis paper discusses a fully decentralized online federated learning setting with long-term constraints. The fully decentralized setting removes communication and computational bottlenecks associated with a central server communicating with a large number of clients. Also, online learning is introduced to the federated learning setting to capture situations with time-varying data distribution. Practical federated learning settings are imposed with long-term constraints such as energy constraints, money cost constraints, time constraints etc. The clients are not obligated to satisfy any per round constraint, but they must satisfy these long-term constraints. To provide privacy to the shared local model updates of the clients, local differential privacy is introduced. An online mirror descent-based algorithm is proposed and its regret bound is obtained. The regret bound is compared with the regret bound of a differentially-private version of online gradient descent algorithm proposed for federated learning.en_US
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.ispartofseries2021 IEEE International Symposium on Information Theory (ISIT);
dc.subjectDifferential privacyen_US
dc.subjectPrivacyen_US
dc.subjectComputational modelingen_US
dc.subjectAggregatesen_US
dc.subjectTraining dataen_US
dc.subjectCollaborative worken_US
dc.subjectServersen_US
dc.titleDifferentially-private federated learning with long-term constraints using online mirror descenten_US
dc.typeConference paperen_US
dc.rights.holderCopyright © 2021, IEEEen_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record