Dynamics of the Fisher information metric

Calmet, Xavier and Calmet, Jaques (2005) Dynamics of the Fisher information metric. Physical Review E, 71 (5). ISSN 1539-3755

[img]
Preview
PDF - Published Version
Download (73kB) | Preview

Abstract

We present a method to generate probability distributions that correspond to metrics obeying partial differential equations generated by extremizing a functional J[g(mu nu)(theta(i))], where g(mu nu)(theta(i)) is the Fisher metric. We postulate that this functional of the dynamical variable g(mu nu)(theta(i)) is stationary with respect to small variations of these variables. Our approach enables a dynamical approach to the Fisher information metric. It allows one to impose symmetries on a statistical system in a systematic way.

Item Type: Article
Additional Information: Article Number: 056109 Part: Part 2
Schools and Departments: School of Mathematical and Physical Sciences > Physics and Astronomy
Depositing User: Xavier Calmet
Date Deposited: 06 Feb 2012 18:13
Last Modified: 10 Mar 2017 04:25
URI: http://sro.sussex.ac.uk/id/eprint/15301

View download statistics for this item

📧 Request an update