On Closed-Form Expressions for the Fisher-Rao Distance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miyamoto, Henrique K., Meneghetti, Fábio C. C., Pinele, Julianna, Costa, Sueli I. R.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910617638535168
author Miyamoto, Henrique K.
Meneghetti, Fábio C. C.
Pinele, Julianna
Costa, Sueli I. R.
author_facet Miyamoto, Henrique K.
Meneghetti, Fábio C. C.
Pinele, Julianna
Costa, Sueli I. R.
contents The Fisher-Rao distance is the geodesic distance between probability distributions in a statistical manifold equipped with the Fisher metric, which is a natural choice of Riemannian metric on such manifolds. It has recently been applied to supervised and unsupervised problems in machine learning, in various contexts. Finding closed-form expressions for the Fisher-Rao distance is generally a non-trivial task, and those are only available for a few families of probability distributions. In this survey, we collect examples of closed-form expressions for the Fisher-Rao distance of both discrete and continuous distributions, aiming to present them in a unified and accessible language. In doing so, we also: illustrate the relation between negative multinomial distributions and the hyperbolic model, include a few new examples, and write a few more in the standard form of elliptical distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2304_14885
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Closed-Form Expressions for the Fisher-Rao Distance
Miyamoto, Henrique K.
Meneghetti, Fábio C. C.
Pinele, Julianna
Costa, Sueli I. R.
Statistics Theory
Information Theory
Differential Geometry
The Fisher-Rao distance is the geodesic distance between probability distributions in a statistical manifold equipped with the Fisher metric, which is a natural choice of Riemannian metric on such manifolds. It has recently been applied to supervised and unsupervised problems in machine learning, in various contexts. Finding closed-form expressions for the Fisher-Rao distance is generally a non-trivial task, and those are only available for a few families of probability distributions. In this survey, we collect examples of closed-form expressions for the Fisher-Rao distance of both discrete and continuous distributions, aiming to present them in a unified and accessible language. In doing so, we also: illustrate the relation between negative multinomial distributions and the hyperbolic model, include a few new examples, and write a few more in the standard form of elliptical distributions.
title On Closed-Form Expressions for the Fisher-Rao Distance
topic Statistics Theory
Information Theory
Differential Geometry
url https://arxiv.org/abs/2304.14885