Mathematical Analysis on Information-Theoretic Metric Learning With Application to Supervised Learning
- 주제(키워드) Bregman iteration , machine learning algorithm , mathematical analysis , metric learning , convex optimization
- 주제(기타) Computer Science, Information Systems; Engineering, Electrical & Electronic; Telecommunications
- 설명문(일반) [Choi, Jooyeon; Min, Chohong] Ewha Womans Univ, Dept Math, Seoul 03760, South Korea; [Lee, Byungjoon] Catholic Univ Korea, Dept Math, Bucheon 14662, South Korea
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- OA유형 gold
- 발행기관 IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- 발행년도 2019
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000166006
- 본문언어 영어
- Published As http://dx.doi.org/10.1109/ACCESS.2019.2937973
초록/요약
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.
more