View : 1028 Download: 406

Mathematical Analysis on Information-Theoretic Metric Learning With Application to Supervised Learning

Title
Mathematical Analysis on Information-Theoretic Metric Learning With Application to Supervised Learning
Authors
Choi, JooyeonMin, ChohongLee, Byungjoon
Ewha Authors
민조홍
SCOPUS Author ID
민조홍scopus
Issue Date
2019
Journal Title
IEEE ACCESS
ISSN
2169-3536JCR Link
Citation
IEEE ACCESS vol. 7, pp. 121998 - 122005
Keywords
Bregman iterationmachine learning algorithmmathematical analysismetric learningconvex optimization
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Indexed
SCIE; SCOPUS WOS
Document Type
Article
Abstract
This 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.
DOI
10.1109/ACCESS.2019.2937973
Appears in Collections:
자연과학대학 > 수학전공 > Journal papers
Files in This Item:
Mathematical Analysis.pdf(2.38 MB) Download
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

BROWSE