View : 203 Download: 38

Full metadata record

DC Field Value Language
dc.contributor.author민조홍-
dc.date.accessioned2020-01-14T16:30:34Z-
dc.date.available2020-01-14T16:30:34Z-
dc.date.issued2019-
dc.identifier.issn2169-3536-
dc.identifier.otherOAK-26200-
dc.identifier.urihttp://dspace.ewha.ac.kr/handle/2015.oak/252444-
dc.description.abstractThis article presents a concrete mathematical analysis on Information-Theoretic Metric Learning (ITML). The analysis provides a theoretical foundation for ITML, by supplying well-posedness, strong duality, and convergence. Our analysis suggests the correction of a typo in the original ITML article that may lead to the loss of accuracy in the metric learning. The necessity of this correction is confirmed by several numerical experiments on supervised learning.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.subjectBregman iteration-
dc.subjectmachine learning algorithm-
dc.subjectmathematical analysis-
dc.subjectmetric learning-
dc.subjectconvex optimization-
dc.titleMathematical Analysis on Information-Theoretic Metric Learning With Application to Supervised Learning-
dc.typeArticle-
dc.relation.volume7-
dc.relation.indexSCIE-
dc.relation.indexSCOPUS-
dc.relation.startpage121998-
dc.relation.lastpage122005-
dc.relation.journaltitleIEEE ACCESS-
dc.identifier.doi10.1109/ACCESS.2019.2937973-
dc.identifier.wosidWOS:000498584600002-
dc.author.googleChoi, Jooyeon-
dc.author.googleMin, Chohong-
dc.author.googleLee, Byungjoon-
dc.contributor.scopusid민조홍(16239287100)-
dc.date.modifydate20200114163026-


qrcode

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

BROWSE