PhysRevE.71.056109.pdf (71.31 kB)
Dynamics of the Fisher information metric
journal contribution
posted on 2023-06-07, 19:16 authored by Xavier CalmetXavier Calmet, Jaques CalmetWe 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.
History
Publication status
- Published
File Version
- Published version
Journal
Physical Review EISSN
1539-3755Publisher
American Physical SocietyExternal DOI
Issue
5Volume
71Department affiliated with
- Physics and Astronomy Publications
Notes
Article Number: 056109 Part: Part 2Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2012-02-06First Open Access (FOA) Date
2016-03-22First Compliant Deposit (FCD) Date
2017-03-10Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC