Standard Divergence in Manifold of Dual Affine Connections

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9389)

Abstract

A divergence function defines a Riemannian metric G and dually coupled affine connections \(\left( \nabla , \nabla ^{*}\right) \) with respect to it in a manifold M. When M is dually flat, a canonical divergence is known, which is uniquely determined from \(\left\{ G, \nabla , \nabla ^{*}\right\} \). We search for a standard divergence for a general non-flat M. It is introduced by the magnitude of the inverse exponential map, where \(\alpha =-(1/3)\) connection plays a fundamental role. The standard divergence is different from the canonical divergence.

References

  1. Amari, S., Nagaoka, H.: Methods of Information Geometry. American Mathematical Society and Oxford University Press, Providence (2000)MATHGoogle Scholar
  2. Eguchi, S.: Second order efficiency of minimum contrast estimators in a curved exponential family. Ann. Stat. 11, 793–803 (1983)MathSciNetCrossRefMATHGoogle Scholar
  3. Matumoto, T.: Any statistical manifold has a contrast function -\(\;\)On the \(C^3\)-functions taking the minimum at the diagonal of the product manifold. Hiroshima Math. J. 23, 327–332 (1993)MathSciNetMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.RIKEN Brain Science InstituteWako-shi, SaitamaJapan
  2. 2.Max-Planck Institute for Mathematics in ScienceLeipzigGermany

Personalised recommendations