A family of statistical symmetric divergences based on Jensen's
inequality
F. Nielsen. (2010)cite arxiv:1009.4004Comment: 15 pages, 2 figure.
Abstract
We introduce a novel parametric family of symmetric information-theoretic
distances based on Jensen's inequality for a convex functional generator. In
particular, this family unifies the celebrated Jeffreys divergence with the
Jensen-Shannon divergence when the Shannon entropy generator is chosen. We then
design a generic algorithm to compute the unique centroid defined as the
minimum average divergence. This yields a smooth family of centroids linking
the Jeffreys to the Jensen-Shannon centroid. Finally, we report on our
experimental results.
Description
[1009.4004] A family of statistical symmetric divergences based on Jensen's inequality
%0 Journal Article
%1 nielsen2010family
%A Nielsen, Frank
%D 2010
%K divergences entropy readings
%T A family of statistical symmetric divergences based on Jensen's
inequality
%U http://arxiv.org/abs/1009.4004
%X We introduce a novel parametric family of symmetric information-theoretic
distances based on Jensen's inequality for a convex functional generator. In
particular, this family unifies the celebrated Jeffreys divergence with the
Jensen-Shannon divergence when the Shannon entropy generator is chosen. We then
design a generic algorithm to compute the unique centroid defined as the
minimum average divergence. This yields a smooth family of centroids linking
the Jeffreys to the Jensen-Shannon centroid. Finally, we report on our
experimental results.
@article{nielsen2010family,
abstract = {We introduce a novel parametric family of symmetric information-theoretic
distances based on Jensen's inequality for a convex functional generator. In
particular, this family unifies the celebrated Jeffreys divergence with the
Jensen-Shannon divergence when the Shannon entropy generator is chosen. We then
design a generic algorithm to compute the unique centroid defined as the
minimum average divergence. This yields a smooth family of centroids linking
the Jeffreys to the Jensen-Shannon centroid. Finally, we report on our
experimental results.},
added-at = {2019-12-11T14:48:28.000+0100},
author = {Nielsen, Frank},
biburl = {https://www.bibsonomy.org/bibtex/298a7ce4e590bb9fecb3df21d0bf1dd49/kirk86},
description = {[1009.4004] A family of statistical symmetric divergences based on Jensen's inequality},
interhash = {5ea92bf5338b649bbcfa04a0dba46257},
intrahash = {98a7ce4e590bb9fecb3df21d0bf1dd49},
keywords = {divergences entropy readings},
note = {cite arxiv:1009.4004Comment: 15 pages, 2 figure},
timestamp = {2019-12-11T14:48:40.000+0100},
title = {A family of statistical symmetric divergences based on Jensen's
inequality},
url = {http://arxiv.org/abs/1009.4004},
year = 2010
}