Fisher-Rao distances between finite-energy signals in Gaussian noise

2025/05/20 by Florin, Franck
#62 #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2505.14611

Abstract

This paper proposes representing finite-energy signals observed within a given bandwidth as parameters of a probability distribution and employing the information-geometric framework to compute the Fisher-Rao distance between these signals, considered as distributions.

Citations

• A Simple Approximation Method for the Fisher–Rao Distance between Multivariate Normal Distributions
• An elementary introduction to information geometry

Related

• Fisher information distance: a geometrical reading
• Fisher information as a performance metric for locally optimum processing
• Schoenberg-Rao distances: Entropy-based and geometry-aware statistical Hilbert distances
• New energy distances for statistical inference on infinite dimensional Hilbert spaces without moment conditions
• Random Field Representations of Kernel Distances