Exact upper and lower bounds on the misclassification probability
Statistics Theory
2018-02-12 v4 Machine Learning
Probability
Statistics Theory
Abstract
Exact lower and upper bounds on the best possible misclassification probability for a finite number of classes are obtained in terms of the total variation norms of the differences between the sub-distributions over the classes. These bounds are compared with the exact bounds in terms of the conditional entropy obtained by Feder and Merhav.
Keywords
Cite
@article{arxiv.1712.00812,
title = {Exact upper and lower bounds on the misclassification probability},
author = {Iosif Pinelis},
journal= {arXiv preprint arXiv:1712.00812},
year = {2018}
}
Comments
Version 3: exact upper bounds are added; results are compared with ones by Feder and Merhav. Version 4: additional discussion presented