ON EXPONENTIAL BOUNDS ON THE BAYES RISK OF THE KERNEL CLASSIFICATION RULE

被引：8
|
作者：
KRZYZAK, A
机构：
[1] Department of Computer Science, Concordia University, Montréal, H3G, 1M8
来源：
IEEE TRANSACTIONS ON INFORMATION THEORY | 1991年 / 37卷 / 03期
基金：
加拿大自然科学与工程研究理事会;
关键词：
KERNEL CLASSIFICATION RULE; L1 STRONG CONSISTENCY; RATES OF STRONG CONVERGENCE; EXPONENTIAL INEQUALITY;
D O I：
10.1109/18.79905
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Improved exponential bounds on Bayes probability of error for the nonparametric kernel classification rule are derived. It is shown, using the martingale device, that weak, strong, and complete L1 Bayes risk consistencies are equivalent. Consequently the conditions on the smoothing sequence h(n) --> 0 and nh(n) --> infinity are necessary and sufficient for Bayes rish consistency of the kernel classification rule. The rate of convergence of the kernel classification rule is also given.
引用
收藏
页码：490 / 499
页数：10
相关论文
共 50 条
  • [1] NECESSARY AND SUFFICIENT CONDITIONS FOR BAYES RISK CONSISTENCY OF A RECURSIVE KERNEL CLASSIFICATION RULE
    GREBLICKI, W
    PAWLAK, M
    IEEE TRANSACTIONS ON INFORMATION THEORY, 1987, 33 (03) : 408 - 412
  • [2] Remarks on kernel Bayes' rule
    Johno, Hisashi
    Nakamoto, Kazunori
    Saigo, Tatsuhiko
    COGENT MATHEMATICS & STATISTICS, 2018, 5 (01):
  • [3] BOUNDS ON THE BAYES CLASSIFICATION ERROR BASED ON PAIRWISE RISK FUNCTIONS
    GARBER, FD
    DJOUADI, A
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1988, 10 (02) : 281 - 288
  • [4] RISK CLASSIFICATION WITH AN ADAPTIVE NAIVE BAYES KERNEL MACHINE MODEL
    Minnier, J.
    Liu, J.
    Cai, T.
    AMERICAN JOURNAL OF EPIDEMIOLOGY, 2011, 173 : S16 - S16
  • [5] Risk Classification With an Adaptive Naive Bayes Kernel Machine Model
    Minnier, Jessica
    Yuan, Ming
    Liu, Jun S.
    Cai, Tianxi
    JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2015, 110 (509) : 393 - 404
  • [6] A Bayes empirical Bayes decision rule for classification
    Li, TF
    Yen, TC
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2005, 34 (05) : 1137 - 1149
  • [7] Exponential estimates for an empirical Bayes risk in classification of a mixture with varying concentrations
    Ivan'ko Yu.O.
    Maiboroda R.E.
    Ukrainian Mathematical Journal, 2002, 54 (10) : 1722 - 1731
  • [8] Importance Weighting Approach in Kernel Bayes' Rule
    Xu, Liyuan
    Chen, Yutian
    Doucet, Arnaud
    Gretton, Arthur
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [9] On Bayes Risk Lower Bounds
    Chen, Xi
    Guntuboyina, Adityanand
    Zhang, Yuchen
    JOURNAL OF MACHINE LEARNING RESEARCH, 2016, 17 : 1 - 58
  • [10] On the Kernel Rule for Function Classification
    C. Abraham
    G. Biau
    B. Cadre
    Annals of the Institute of Statistical Mathematics, 2006, 58 : 619 - 633
12345