Jump to content

Chentsov's theorem

Add links
From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Compsonheir (talk | contribs) at 23:40, 11 January 2022 (←Created page with 'In information geometry, '''Chentsov's theorem''' states that the Fisher information metric is, up to rescaling, the unique Riemannian metric on a statistical manifold that is invariant under sufficient statistics. == See also == *Fisher information *Sufficient statistic *Information geometry == References == * {{cite journal |doi=10.1007/s41884-018-0006-4|title=Chentsov's theorem for exponential families|year=2018|last1=...'). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

In information geometry, Chentsov's theorem states that the Fisher information metric is, up to rescaling, the unique Riemannian metric on a statistical manifold that is invariant under sufficient statistics.

See also

References

  • Dowty, James G. (2018). "Chentsov's theorem for exponential families". Information Geometry. 1 (1): 117-135. arXiv:1701.08895. doi:10.1007/s41884-018-0006-4.
  • Shun'ichi Amari, Hiroshi Nagaoka (2000) Methods of information geometry, Translations of mathematical monographs; v. 191, American Mathematical Society.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Chentsov%27s_theorem&oldid=1065124121"