Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Quantized Distributed Online Kernel Learning

Full metadata record
DC Field Value Language
dc.contributor.authorPark, Jonghwan-
dc.contributor.authorHong, Songnam-
dc.date.accessioned2022-07-06T10:54:51Z-
dc.date.available2022-07-06T10:54:51Z-
dc.date.created2022-01-26-
dc.date.issued2021-12-
dc.identifier.issn2162-1233-
dc.identifier.urihttps://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/140083-
dc.description.abstractIn this paper we propose a communication-efficient kernel-based learning method by means of random-feature approximation and quantization. The proposed algorithm is named quantized distributed online kernel learning (QDOKL). We theoretically prove that QDOKL over N time slots can achieve an optimal sublinear regret \mathrm{O}(\sqrt{N}), provided that a quantization level scales with \sqrt{N}. Our analysis implies that every node in the network can learn a common function having a diminishing gap from the best function in hindsight. We verify our theoretical result via numerical tests with real datasets on online regression tasks. Also, it is demonstrated that QDOKL can achieve the almost same accuracy as the unquantized counterpart while having a lower communication overhead.-
dc.language영어-
dc.language.isoen-
dc.publisherIEEE Computer Society-
dc.titleQuantized Distributed Online Kernel Learning-
dc.typeArticle-
dc.contributor.affiliatedAuthorHong, Songnam-
dc.identifier.doi10.1109/ICTC52510.2021.9620759-
dc.identifier.scopusid2-s2.0-85122939976-
dc.identifier.wosid000790235800085-
dc.identifier.bibliographicCitationInternational Conference on ICT Convergence, v.2021, no.October, pp.357 - 361-
dc.relation.isPartOfInternational Conference on ICT Convergence-
dc.citation.titleInternational Conference on ICT Convergence-
dc.citation.volume2021-
dc.citation.numberOctober-
dc.citation.startPage357-
dc.citation.endPage361-
dc.type.rimsART-
dc.type.docTypeProceedings Paper-
dc.description.journalClass1-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.subject.keywordPlusE-learning-
dc.subject.keywordPlusDistributed learning-
dc.subject.keywordPlusEfficient kernels-
dc.subject.keywordPlusFeature approximation-
dc.subject.keywordPlusFeature quantizations-
dc.subject.keywordPlusKernel-based learning-
dc.subject.keywordPlusLearning methods-
dc.subject.keywordPlusOnline kernel learning-
dc.subject.keywordPlusOnline learning-
dc.subject.keywordPlusRandom features-
dc.subject.keywordPlusTimeslots-
dc.subject.keywordPlusLearning systems-
dc.subject.keywordAuthordistributed learning-
dc.subject.keywordAuthorkernel-based learning-
dc.subject.keywordAuthorOnline learning-
dc.identifier.urlhttps://ieeexplore.ieee.org/document/9620759-
Files in This Item
Go to Link
Appears in
Collections
서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Hong, Song nam photo

Hong, Song nam
COLLEGE OF ENGINEERING (SCHOOL OF ELECTRONIC ENGINEERING)
Read more

Altmetrics

Total Views & Downloads

BROWSE