Fisher information distance: a geometrical reading

Abstract

This paper is a strongly geometrical approach to the Fisher distance, which is a measure of dissimilarity between two probability distribution functions. The Fisher distance, as well as other divergence measures, are also used in many applications to establish a proper data average. The main purpose is to widen the range of possible interpretations and relations of the Fisher distance and its associated geometry for the prospective applications. It focuses on statistical models of the normal probability distribution functions and takes advantage of the connection with the classical hyperbolic geometry to derive closed forms for the Fisher distance in several cases. Connections with the well-known Kullback-Leibler divergence measure are also devised.

15 pages, 8 figures

Cited by in corpus (7)

• Entanglement entropy and Fisher information metric for closed bosonic strings in homogeneous plane wave background
• Information Geometry and Sequential Monte Carlo
• Hyperbolic Deep Learning for Chinese Natural Language Understanding
• Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
• The Shape Metric for Clustering Algorithms
• Geodesic Exponential Kernels: When Curvature and Linearity Conflict
• SMML estimators for linear regression and tessellations of hyperbolic space