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

被引:0
|
作者
Choi, Jooyeon [1 ]
Min, Chohong [1 ]
Lee, Byungjoon [2 ]
机构
[1] Ewha Womans Univ, Dept Math, Seoul 03760, South Korea
[2] Catholic Univ Korea, Dept Math, Bucheon 14662, South Korea
基金
新加坡国家研究基金会;
关键词
Bregman iteration; machine learning algorithm; mathematical analysis; metric learning; convex optimization; PERSON REIDENTIFICATION;
D O I
10.1109/ACCESS.2019.2937973
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:121998 / 122005
页数:8
相关论文
共 50 条
  • [1] Information-Theoretic Semi-Supervised Metric Learning via Entropy Regularization
    Niu, Gang
    Dai, Bo
    Yamada, Makoto
    Sugiyama, Masashi
    [J]. NEURAL COMPUTATION, 2014, 26 (08) : 1717 - 1762
  • [2] One-epoch learning for supervised information-theoretic competitive learning
    Kamimura, R
    [J]. NEURAL INFORMATION PROCESSING, 2004, 3316 : 524 - 529
  • [3] Distributed Information-Theoretic Metric Learning in Apache Spark
    Su, Yuxin
    Yang, Haiqin
    King, Irwin
    Lyu, Michael
    [J]. 2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 3306 - 3313
  • [4] Information-theoretic analysis for transfer learning
    Wu, Xuetong
    Manton, Jonathan H.
    Aickelin, Uwe
    Zhu, Jingge
    [J]. 2020 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2020, : 2819 - 2824
  • [5] Efficient Information-Theoretic Large-Scale Semi-Supervised Metric Learning via Proxies
    Chen, Peng
    Wang, Huibing
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (15):
  • [6] On the Generalization for Transfer Learning: An Information-Theoretic Analysis
    Wu, Xuetong
    Manton, Jonathan H.
    Aickelin, Uwe
    Zhu, Jingge
    [J]. IEEE Transactions on Information Theory, 2024, 70 (10) : 7089 - 7124
  • [7] An Information-Theoretic Analysis of Bayesian Reinforcement Learning
    Gouverneur, Amaury
    Rodriguez-Galvez, Borja
    Oechtering, Tobias J.
    Skoglund, Mikael
    [J]. 2022 58TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2022,
  • [8] Information-Theoretic Odometry Learning
    Sen Zhang
    Jing Zhang
    Dacheng Tao
    [J]. International Journal of Computer Vision, 2022, 130 : 2553 - 2570
  • [9] Information-theoretic competitive learning
    Kamimura, R
    [J]. IASTED: PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON MODELLING AND SIMULATION, 2003, : 359 - 365
  • [10] Information-Theoretic Odometry Learning
    Zhang, Sen
    Zhang, Jing
    Tao, Dacheng
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (11) : 2553 - 2570