Metrization of powers of the Jensen-Shannon divergence

02/20/2023
by   Kazuki Okamura, et al.
0

Metrization of statistical divergences is useful in both theoretical and practical aspects. Considering the fractional powers of statistical divergences is one way to obtain metrics associated with divergences. With this motivation, Osán, Bussandri, and Lamberti (2018) considered metrizations for the fractional powers of the Jensen-Shannon divergences between multinomial distributions and gave an open problem. In this short note, we give an affirmative answer to their conjecture. This method is also applicable to powers of f-divergences between the Cauchy distribution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2018

A Short Note on the Jensen-Shannon Divergence between Simple Mixture Distributions

This short note presents results about the symmetric Jensen-Shannon dive...
research
02/01/2018

On a fractional version of Haemers' bound

In this note, we present a fractional version of Haemers' bound on the S...
research
06/30/2018

The asymptotic spectrum of graphs and the Shannon capacity

We introduce the asymptotic spectrum of graphs and apply the theory of a...
research
09/22/2022

A second moment proof of the spread lemma

This note concerns a well-known result which we term the “spread lemma,”...
research
02/19/2021

On a Variational Definition for the Jensen-Shannon Symmetrization of Distances based on the Information Radius

We generalize the Jensen-Shannon divergence by considering a variational...
research
09/21/2010

A family of statistical symmetric divergences based on Jensen's inequality

We introduce a novel parametric family of symmetric information-theoreti...
research
10/28/2008

A non-negative expansion for small Jensen-Shannon Divergences

In this report, we derive a non-negative series expansion for the Jensen...

Please sign up or login with your details

Forgot password? Click here to reset