Asymmetric topologies on statistical manifolds

DOI10.1007/978-3-319-25040-3_23MaRDI QIDQ2807517zbMATH OpenOpenAlexFDO

Authors Roman V. Belavkin

Publication date 25 May 2016

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1507.08229

Mathematics Subject Classification ID

Measures of information, entropy (94A17)

Abstract: Asymmetric information distances are used to define asymmetric norms and quasimetrics on the statistical manifold and its dual space of random variables. Quasimetric topology, generated by the Kullback-Leibler (KL) divergence, is considered as the main example, and some of its topological properties are investigated.

Recommendations

• Manifolds of differentiable densities
• On asymmetric \(I\) and \(I^*\)-divergence
• scientific article; zbMATH DE number 124792
• On asymmetric distances
• Differential-geometrical methods in statistics

Cited in

(5)

• On the well-posedness of Bayesian inverse problems
• When optimal transport meets information geometry
• Properties of relative asymmetric near-metric spaces and applications
• Bayesian Inverse Problems Are Usually Well-Posed
• A historical perspective on Schützenberger-Pinsker inequalities (extended version)

This page was built for publication: Asymmetric topologies on statistical manifolds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2807517)