Document Type
Article
Journal/Book Title/Conference
Entropy
Volume
21
Issue
12
Publisher
M D P I AG
Publication Date
11-23-2019
First Page
1
Last Page
42
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Abstract
Bounding the best achievable error probability for binary classification problems is relevant to many applications including machine learning, signal processing, and information theory. Many bounds on the Bayes binary classification error rate depend on information divergences between the pair of class distributions. Recently, the Henze–Penrose (HP) divergence has been proposed for bounding classification error probability. We consider the problem of empirically estimating the HP-divergence from random samples. We derive a bound on the convergence rate for the Friedman–Rafsky (FR) estimator of the HP-divergence, which is related to a multivariate runs statistic for testing between two distributions. The FR estimator is derived from a multicolored Euclidean minimal spanning tree (MST) that spans the merged samples. We obtain a concentration inequality for the Friedman–Rafsky estimator of the Henze–Penrose divergence. We validate our results experimentally and illustrate their application to real datasets.
Recommended Citation
Sekeh, S.Y.; Noshad, M.; Moon, K.R.; Hero, A.O. Convergence Rates for Empirical Estimation of Binary Classification Bounds. Entropy 2019, 21, 1144.
