Generalized Maximum Entropy for Supervised Classification

被引:12
|
作者
Mazuelas, Santiago [1 ,2 ]
Shen, Yuan [3 ,4 ]
Perez, Aritz [1 ]
机构
[1] Basque Ctr Appl Math BCAM, Bilbao 48009, Spain
[2] IKERBASQUE Basque Fdn Sci, Bilbao 48009, Spain
[3] Tsinghua Univ, Dept Elect Engn, Beijing 100190, Peoples R China
[4] Beijing Natl Res Ctr Informat Sci & Technol, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
Entropy; Uncertainty; Probability distribution; Training; Codes; Channel coding; Decision making; Supervised classification; minimax risk classifiers; maximum entropy; generalized entropy;
D O I
10.1109/TIT.2022.3143764
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The maximum entropy principle advocates to evaluate events' probabilities using a distribution that maximizes entropy among those that satisfy certain expectations' constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper establishes a framework for supervised classification based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). We develop learning techniques that determine MRCs for general entropy functions and provide performance guarantees by means of convex optimization. In addition, we describe the relationship of the presented techniques with existing classification methods, and quantify MRCs performance in comparison with the proposed bounds and conventional methods.
引用
收藏
页码:2530 / 2550
页数:21
相关论文
共 50 条
  • [1] Generalized Maximum Entropy Principle, Superstatistics and Problem of Networks Classification
    Gadjiev, Bahruz
    [J]. BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING, 2010, 1305 : 407 - 414
  • [2] Generalized maximum entropy
    Cheeseman, P
    Stutz, J
    [J]. BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING, 2005, 803 : 374 - 381
  • [3] Generalized maximum entropy estimation
    Sutter, Tobias
    Sutter, David
    Esfahani, Peyman Mohajerin
    Lygeros, John
    [J]. Journal of Machine Learning Research, 2019, 20
  • [4] Generalized maximum entropy estimation
    Sutter, Tobias
    Sutter, David
    Esfahani, Peyman Mohajerin
    Lygeros, John
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2019, 20
  • [5] The generalized maximum belief entropy model
    Siran Li
    Rui Cai
    [J]. Soft Computing, 2022, 26 : 4187 - 4198
  • [6] GENERALIZED MAXIMUM-ENTROPY PRINCIPLE
    THOMAS, MU
    [J]. OPERATIONS RESEARCH, 1979, 27 (06) : 1188 - 1196
  • [7] THE GENERALIZED MAXIMUM-ENTROPY PRINCIPLE
    KESAVAN, HK
    KAPUR, JN
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1989, 19 (05): : 1042 - 1052
  • [8] Duality in a maximum generalized entropy model
    Eguchi, Shinto
    Komori, Osamu
    Ohara, Atsumi
    [J]. BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING (MAXENT 2014), 2015, 1641 : 297 - 304
  • [9] The generalized maximum belief entropy model
    Li, Siran
    Cai, Rui
    [J]. SOFT COMPUTING, 2022, 26 (09) : 4187 - 4198
  • [10] Maximum entropy in the generalized moment problem
    Frontini, M
    Tagliani, A
    [J]. JOURNAL OF MATHEMATICAL PHYSICS, 1998, 39 (12) : 6706 - 6714