Fisher information distance: a geometrical reading

DOI10.1016/J.DAM.2014.10.004zbMATH Open1329.94027arXiv1210.2354OpenAlexW2017203286MaRDI QIDQ499362FDOQ499362

Authors: Sueli I. R. Costa, S. A. Santos, João E. Strapasson 

Publication date: 30 September 2015

Published in: Discrete Applied Mathematics (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1210.2354

Recommendations

• Relations between Renyi distance and Fisher information
• Geometric mean of probability measures and geodesics of Fisher information metric
• Fisher information geometry of the barycenter map
• Distance in variation and a Fisher-type information
• An identity for the Fisher information and Mahalanobis distance
• Fisher information metric based on stochastic neighbor embedding
• The uniqueness of the Fisher metric as information metric
• Fisher information metric and Poisson kernels

zbMATH Keywords

Kullback-Leibler divergencehyperbolic geometryinformation geometryFisher distancenormal probability distribution functions

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Measures of information, entropy (94A17) Distribution theory (60E99)

Cites Work

• The elements of statistical learning. Data mining, inference, and prediction
• On Information and Sufficiency
• Title not available (Why is that?)
• Sided and Symmetrized Bregman Centroids
• Title not available (Why is that?)
• Title not available (Why is that?)
• Euclidean distance geometry and applications
• Fisher in 1921
• Information theoretic inequalities
• Morphological processing of univariate Gaussian distribution-valued images based on Poincaré upper-half plane representation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multivariate normal distributions parametrized as a Riemannian symmetric space
• On the similarity of the entropy power inequality and the Brunn- Minkowski inequality (Corresp.)
• Multivariate texture discrimination based on geodesics to class centroids on a generalized Gaussian manifold
• The interval branch-and-prune algorithm for the discretizable molecular distance geometry problem with inexact distances
• A distance between multivariate normal distributions based in an embedding into the Siegel group
• Ford and Dirichlet Regions for Fuchsian Groups
• K-Centroids-Based Supervised Classification of Texture Images Using the SIRV Modeling

Cited In (29)

• Fisher information metric based on stochastic neighbor embedding
• Geometric relations in classical and quantum information theory using the Lambert-Tsallis \(W_q(x)\) function
• Barycentric subspace analysis on manifolds
• Alpha geodesic distances for clustering of shapes
• Random matrix-improved estimation of covariance matrix distances
• Information geometry, simulation and complexity in Gaussian random fields
• An Information Geometry Approach to Robustness Analysis for the Uncertainty Quantification of Computer Codes
• Preface
• Applications of distance between probability distributions to gravitational wave data analysis
• Parametric information geometry with the package Geomstats
• Complexity of mixed Gaussian states from Fisher information geometry
• A shape distance based on the Fisher-Rao metric and its application for shapes clustering
• Geometric mean of probability measures and geodesics of Fisher information metric
• The Fisher-Rao loss for learning under label noise
• Information metrics for phylogenetic trees via distributions of discrete and continuous characters
• The maximal Strichartz family of Gaussian distributions: Fisher information, index of dispersion, and stochastic ordering
• Computing distances and geodesics between manifold-valued curves in the SRV framework
• Fisher information geometry of the barycenter map
• Stochastic modified flows for Riemannian stochastic gradient descent
• On closed-form expressions for the Fisher-Rao distance
• The geometry of off-the-grid compressed sensing
• On some connections between Esscher's tilting, saddlepoint approximations, and optimal transportation: a statistical perspective
• One-parameter generalised Fisher information matrix: one random variable
• On the Fisher-Rao information metric in the space of normal distributions
• Fisher information of the Kuramoto model: a geometric reading on synchronization
• A parallel Douglas-Rachford algorithm for minimizing ROF-like functionals on images with values in symmetric Hadamard manifolds
• An identity for the Fisher information and Mahalanobis distance
• Dynamics of hierarchical clustering in stocks market during financial crises
• Information geometry and asymptotic geodesics on the space of normal distributions

Uses Software

• ElemStatLearn

This page was built for publication: Fisher information distance: a geometrical reading

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q499362)