"A Probabilistic Upper Bound on Differential Entropy" by Joseph DeStefano

Selected Works of Erik G Learned-Miller

Follow Contact

Article

A Probabilistic Upper Bound on Differential Entropy

University of Massachusetts - Amherst Technical Report (2005)

Joseph DeStefano, University of Massachusetts - Amherst
Erik G Learned-Miller, University of Massachusetts - Amherst

Download Find in your library

Abstract

A novel probabilistic upper bound on the entropy of an unknown one-dimensional distribution, given the support of the distribution and a sample from that distribution, is presented. No knowledge beyond the support of the unknown distribution is required. Previous distribution-free bounds on the cumulative distribution function of a random variable given a sample of that variable are used to construct the bound. A simple, fast, and intuitive algorithm for computing the entropy bound from a sample is provided.

Disciplines

Computer Sciences

Publication Date

2005

Publisher Statement

doi: 10.1109/TIT.2008.929937

Citation Information

Joseph DeStefano and Erik G Learned-Miller. "A Probabilistic Upper Bound on Differential Entropy" University of Massachusetts - Amherst Technical Report Vol. 05 Iss. 12 (2005)
Available at: http://works.bepress.com/erik_learned_miller/21/