Hostname: page-component-77c89778f8-gq7q9 Total loading time: 0 Render date: 2024-07-24T22:48:58.323Z Has data issue: false hasContentIssue false

Hooke’s law in statistical manifolds and divergences

Published online by Cambridge University Press:  22 January 2016

Masayuki Henmi
Affiliation:
Sūgaku Kōbō, 3-2 Surugadai, Kanda, Chiyoda-ku, Tokyo, 101-0062, Japan, m96005b@math.nagoya-u.ac.jp
Ryoichi Kobayashi
Affiliation:
Graduate School of Mathematices, Nagoya University, Chikusa-ku, Nagoya, 464-8602, Japan, ryoichi@math.nagoya-u.ac.jp
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The concept of the canonical divergence is defined for dually flat statistical manifolds in terms of the Legendre transform between dual affine coordinates. In this article, we introduce a new two point function defined for any triple (g,∇, ∇*) of a Riemannian metric g and two affine connections ∇ and ∇*. We show that this interprets the canonical divergence without refering to the existence of special coordinates (dual affine coordinates) but in terms of only classical mechanics concerning ∇- and ∇*-geodesics. We also discuss the properties of the two point function and show that this shares some important properties with the canonical divergence defined on dually flat statistical manifolds.

Keywords

Type
Research Article
Copyright
Copyright © Editorial Board of Nagoya Mathematical Journal 2000

References

[A] Amari, S., Differential-Geometrical Methods in Statistics, Springer Lecture Notes in Statistics 28, 1985.Google Scholar
[A-N] Amari, S. and Nagaoka, H., Method of Information Geometry, to appear, AMS.Google Scholar
[E] Eguchi, S., Geometry of minimum contrast, Hiroshima J. Math, 22 (1992), 631647.Google Scholar
[N-A] Nagaoka, H. and Amari, S., Differential geometry of smooth families of probability distributions, METR, 827, University of Tokyo.Google Scholar