On the Chi square and higher-order Chi distances for approximating
f-divergences
F. Nielsen, und R. Nock. (2013)cite arxiv:1309.3029Comment: 11 pages, two tables, no figure. Java(TM) code available online at http://www.informationgeometry.org/fDivergence/.
DOI: 10.1109/LSP.2013.2288355
Zusammenfassung
We report closed-form formula for calculating the Chi square and higher-order
Chi distances between statistical distributions belonging to the same
exponential family with affine natural space, and instantiate those formula for
the Poisson and isotropic Gaussian families. We then describe an analytic
formula for the $f$-divergences based on Taylor expansions and relying on an
extended class of Chi-type distances.
Beschreibung
[1309.3029] On the Chi square and higher-order Chi distances for approximating f-divergences
%0 Journal Article
%1 nielsen2013square
%A Nielsen, Frank
%A Nock, Richard
%D 2013
%K approximate divergences entropy information readings theory
%R 10.1109/LSP.2013.2288355
%T On the Chi square and higher-order Chi distances for approximating
f-divergences
%U http://arxiv.org/abs/1309.3029
%X We report closed-form formula for calculating the Chi square and higher-order
Chi distances between statistical distributions belonging to the same
exponential family with affine natural space, and instantiate those formula for
the Poisson and isotropic Gaussian families. We then describe an analytic
formula for the $f$-divergences based on Taylor expansions and relying on an
extended class of Chi-type distances.
@article{nielsen2013square,
abstract = {We report closed-form formula for calculating the Chi square and higher-order
Chi distances between statistical distributions belonging to the same
exponential family with affine natural space, and instantiate those formula for
the Poisson and isotropic Gaussian families. We then describe an analytic
formula for the $f$-divergences based on Taylor expansions and relying on an
extended class of Chi-type distances.},
added-at = {2019-12-11T14:39:50.000+0100},
author = {Nielsen, Frank and Nock, Richard},
biburl = {https://www.bibsonomy.org/bibtex/238c8b91d7fac65f300dc1ef062d98e29/kirk86},
description = {[1309.3029] On the Chi square and higher-order Chi distances for approximating f-divergences},
doi = {10.1109/LSP.2013.2288355},
interhash = {4c122f8bea58d75155a922d10c5061aa},
intrahash = {38c8b91d7fac65f300dc1ef062d98e29},
keywords = {approximate divergences entropy information readings theory},
note = {cite arxiv:1309.3029Comment: 11 pages, two tables, no figure. Java(TM) code available online at http://www.informationgeometry.org/fDivergence/},
timestamp = {2019-12-11T14:39:50.000+0100},
title = {On the Chi square and higher-order Chi distances for approximating
f-divergences},
url = {http://arxiv.org/abs/1309.3029},
year = 2013
}