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
  • [31] EXPONENTIAL BOUNDS OF MEAN ERROR FOR THE KERNEL ESTIMATES OF REGRESSION-FUNCTIONS
    ZHAO, LC
    JOURNAL OF MULTIVARIATE ANALYSIS, 1989, 29 (02) : 260 - 273
  • [32] Improved Bounds for the Nystrom Method With Application to Kernel Classification
    Jin, Rong
    Yang, Tianbao
    Mahdavi, Mehrdad
    Li, Yu-Feng
    Zhou, Zhi-Hua
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2013, 59 (10) : 6939 - 6949
  • [33] Integrating associative rule-based classification with Naive Bayes for text classification
    Hadi, Wa'el
    Al-Radaideh, Qasem A.
    Alhawari, Samer
    APPLIED SOFT COMPUTING, 2018, 69 : 344 - 356
  • [34] Convexity, classification, and risk bounds
    Bartlett, PL
    Jordan, MI
    McAuliffe, JD
    JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2006, 101 (473) : 138 - 156
  • [35] The Fermi paradox, Bayes' rule, and existential risk management
    Miller, James D.
    Felton, D.
    FUTURES, 2017, 86 : 44 - 57
  • [36] Bayes' Rule and Bank Credit Game Risk Analysis
    Yang Yanbing
    Liu Bin
    2013 FIFTH INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION (ICMTMA 2013), 2013, : 335 - 337
  • [37] On the Consistency of Kernel Classification Rule for Functional Random Field
    Younso, Ahmad
    JOURNAL OF THE SFDS, 2018, 159 (01): : 68 - 87
  • [38] Bounds for the Bayes error in classification: a Bayesian approach using discriminant analysis
    Pham-Gia, T.
    Turkkan, N.
    Bekker, A.
    STATISTICAL METHODS AND APPLICATIONS, 2007, 16 (01): : 7 - 26
  • [39] Bounds for the Bayes Error in Classification: A Bayesian Approach Using Discriminant Analysis
    T. Pham-Gia
    N. Turkkan
    A. Bekker
    Statistical Methods and Applications, 2007, 16 : 7 - 26
  • [40] Rate-Distortion Bounds on Bayes Risk in Supervised Learning
    Nokleby, Matthew
    Beirami, Ahmad
    Calderbank, Robert
    2016 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, 2016, : 2099 - 2103
12345