Confidence Intervals for the Mutual Information
Information Theory
2013-01-29 v2 math.IT
Abstract
By combining a bound on the absolute value of the difference of mutual information between two joint probablity distributions with a fixed variational distance, and a bound on the probability of a maximal deviation in variational distance between a true joint probability distribution and an empirical joint probability distribution, confidence intervals for the mutual information of two random variables with finite alphabets are established. Different from previous results, these intervals do not need any assumptions on the distribution and the sample size.
Cite
@article{arxiv.1301.5942,
title = {Confidence Intervals for the Mutual Information},
author = {A. G. Stefani and J. B. Huber and C. Jardin and H. Sticht},
journal= {arXiv preprint arXiv:1301.5942},
year = {2013}
}
Comments
5 pages, 2 figure