A characterization of the alpha-connections on the statistical manifold of normal distributions
Hitoshi Furuhata, Jun-ichi Inoguchi, Shimpei Kobayashi

TL;DR
This paper explores the geometric structure of the statistical manifold of normal distributions, revealing its homogeneity and Lie group structure, and characterizes the alpha-connections within this framework.
Contribution
It provides a geometric characterization of alpha-connections on the normal distribution manifold, highlighting its homogeneous Lie group structure.
Findings
Normal distributions form a homogeneous manifold.
The manifold admits a 2D solvable Lie group structure.
Alpha-connections are characterized geometrically on this Lie group.
Abstract
We show that the statistical manifold of normal distributions is homogeneous. In particular, it admits a -dimensional solvable Lie group structure. In addition, we give a geometric characterization of the Amari-Chentsov -connections on the Lie group.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGeometric Analysis and Curvature Flows · Advanced Algebra and Geometry · Topological and Geometric Data Analysis
