On a New Class of Bounds on Bayes Risk in Multihypothesis Pattern Recognition

@article{Devijver1974OnAN,
  title={On a New Class of Bounds on Bayes Risk in Multihypothesis Pattern Recognition},
  author={Pierre A. Devijver},
  journal={IEEE Transactions on Computers},
  year={1974},
  volume={C-23},
  pages={70-80}
}
  • Pierre A. Devijver
  • Published in
    IEEE Transactions on…
    1974
  • Mathematics, Computer Science
  • An important measure concerning the use of statistical decision schemes is the error probability associated with the decision rule. Several methods giving bounds on the error probability are presently available, but, most often, the bounds are loose. Those methods generally make use of so-cailed distances between statistical distributions. In this paper a new distance is proposed which permits tighter bounds to be set on the error probability of the Bayesian decision rule and which is shown to… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 28 CITATIONS

    Success Rates and Posterior Probabilities in Multiple Hypothesis Tracking

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    A general class of lower bounds on the probability of error in multiple hypothesis testing

    VIEW 9 EXCERPTS
    CITES RESULTS, BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Generalized error bounds in pattern recognition

    VIEW 6 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Upper and Lower Tight Error Bounds for Feature Omission with an Extension to Context Reduction

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Arimoto–Rényi Conditional Entropy and Bayesian $M$ -Ary Hypothesis Testing

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Arimoto-Rényi conditional entropy and Bayesian hypothesis testing

    • Igal Sason, Sergio Verdú
    • Mathematics, Computer Science
    • 2017 IEEE International Symposium on Information Theory (ISIT)
    • 2017
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Error bounds for context reduction and feature omission

    VIEW 2 EXCERPTS
    CITES BACKGROUND