Exact upper and lower bounds on the misclassification probability
arXiv:1712.00812
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.
Version 3: exact upper bounds are added; results are compared with ones by Feder and Merhav. Version 4: additional discussion presented