English

On the Chi square and higher-order Chi distances for approximating f-divergences

Information Theory 2015-06-17 v2 math.IT

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 ff-divergences based on Taylor expansions and relying on an extended class of Chi-type distances.

Keywords

Cite

@article{arxiv.1309.3029,
  title  = {On the Chi square and higher-order Chi distances for approximating f-divergences},
  author = {Frank Nielsen and Richard Nock},
  journal= {arXiv preprint arXiv:1309.3029},
  year   = {2015}
}

Comments

11 pages, two tables, no figure. Java(TM) code available online at http://www.informationgeometry.org/fDivergence/