Elsevier

Information Sciences

Volume 25, Issue 1, October 1981, Pages 21-35
Information Sciences

A class of lower bounds on the Bayesian probability of error

https://doi.org/10.1016/0020-0255(81)90009-8Get rights and content

Abstract

In this paper a class of lower bounds is considered which unifies and extends some well-known bounds on the Bayesian probability of error. This class is obtained by considering the ƒ-divergence between two hypotheses. Both the symmetric and the nonsymmetric case are studied.

References (10)

  • D.E. Boekee et al.

    Some aspects of error bounds in feature selection

    Pattern Recognition

    (1979)
  • C.H. Chen

    On information measures and distance measures, error bounds, and feature selection

    Information Sci.

    (1976)
  • I. Csiszar

    Information-type measures of difference of probability distributions and indirect observations

    Studia Sci. Math. Hungar.

    (1967)
  • L. Györfi et al.

    On the dissimilarity of probability measures

  • T. Kailath

    The divergence and Bhattacharyya distance in signal selection

    IEEE Trans. Comm. Tech.

    (1967)
There are more references available in the full text version of this article.

Cited by (9)

  • Robustness of likelihood ratio tests: Hypothesis testing under incorrect models

    2001, Conference Record of the Asilomar Conference on Signals, Systems and Computers
  • Mutual and Conditional mutual informations for optimizing distributed bayes detectors

    2001, IEEE Transactions on Aerospace and Electronic Systems
View all citing articles on Scopus
View full text