Show simple item record

dc.contributor.authorTekin, C.en_US
dc.contributor.authorZhang, S.en_US
dc.contributor.authorSchaar, Mihaela van deren_US
dc.date.accessioned2019-02-13T08:18:04Z
dc.date.available2019-02-13T08:18:04Z
dc.date.issued2015-05-01en_US
dc.identifier.issn1053-587X
dc.identifier.urihttp://hdl.handle.net/11693/49389
dc.description.abstractAbstract—In this paper, we develop online learning algorithms that enable the agents to cooperatively learn how to maximize the overall reward in scenarios where only noisy global feedback is available without exchanging any information among themselves. We prove that our algorithms' learning regrets—the losses incurred by the algorithms due to uncertainty—are logarithmically increasing in time and thus the time average reward converges to the optimal average reward. Moreover, we also illustrate how the regret depends on the size of the action space, and we show that this relationship is influenced by the informativeness of the reward structure with regard to each agent's individual action. When the overall reward is fully informative, regret is shown to be linear in the total number of actions of all the agents. When the reward function is not informative, regret is linear in the number of joint actions. Our analytic and numerical results show that the proposed learning algorithms significantly outperform existing online learning solutions in terms of regret and learning speed. We illustrate how our theoretical framework can be used in practice by applying it to online Big Data mining using distributed classifiers.en_US
dc.language.isoEnglishen_US
dc.source.titleIEEE Transactions on Signal Processingen_US
dc.relation.isversionofhttp://doi.org/10.1109/TSP.2015.2403288en_US
dc.subjectBig data miningen_US
dc.subjectDistributed cooperative learningen_US
dc.subjectMultiagent learningen_US
dc.subjectMultiarmed banditsen_US
dc.subjectOnline learningen_US
dc.subjectReward informativenessen_US
dc.titleDistributed multi-agent online learning based on global feedbacken_US
dc.typeArticleen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.citation.spage2225en_US
dc.citation.epage2238en_US
dc.citation.volumeNumber63en_US
dc.citation.issueNumber9en_US
dc.identifier.doi10.1109/TSP.2015.2403288en_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.identifier.eissn1941-0476


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record