Exact upper and lower bounds on the misclassification probability

Authors

Iosif Pinelis, Michigan Technological UniversityFollow

Document Type

Article

Publication Date

7-2019

Department

Department of Mathematical Sciences

Abstract

Exact upper and lower 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 upper and lower bounds in terms of the conditional entropy obtained by Feder and Merhav.

Publisher's Statement

© 2019 IEEE. Publisher’s version of record: https://doi.org/10.1109/TIT.2019.2891529

Publication Title

IEEE Transactions on Information Theory

Recommended Citation

Pinelis, I. (2019). Exact upper and lower bounds on the misclassification probability. IEEE Transactions on Information Theory, 65(7), 4327-4334. http://doi.org/10.1109/TIT.2019.2891529
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/596