Empirically Estimable Classification Bounds Based on a New Divergence Measure
Information Theory
2015-02-11 v2 math.IT
Machine Learning
Abstract
Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the same distribution and for the case where there exists some mismatch between training and test distributions. We confirm the theoretical results by designing feature selection algorithms using the criteria from these bounds and by evaluating the algorithms on a series of pathological speech classification tasks.
Cite
@article{arxiv.1412.6534,
title = {Empirically Estimable Classification Bounds Based on a New Divergence Measure},
author = {Visar Berisha and Alan Wisler and Alfred O. Hero and Andreas Spanias},
journal= {arXiv preprint arXiv:1412.6534},
year = {2015}
}
Comments
12 pages, 5 figures