On the Chi square and higher-order Chi distances for approximating f-divergences

Abstract

We report closed-form formula for calculating the Chi square and higher-order Chi distances between statistical distributions belonging to the same exponential family with affine natural space, and instantiate those formula for the Poisson and isotropic Gaussian families. We then describe an analytic formula for the $f$-divergences based on Taylor expansions and relying on an extended class of Chi-type distances.

11 pages, two tables, no figure. Java(TM) code available online at http://www.informationgeometry.org/fDivergence/

References in corpus (1)

• Note on exponential families of distributions

Cited by in corpus (19)

• On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means
• An elementary introduction to information geometry
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• Guaranteed bounds on the Kullback-Leibler divergence of univariate mixtures using piecewise log-sum-exp inequalities
• On a Variational Definition for the Jensen-Shannon Symmetrization of Distances based on the Information Radius
• The MadNIS Reloaded
• On Hölder projective divergences
• ELSA -- Enhanced latent spaces for improved collider simulations
• Differentiable MadNIS-Lite
• Mathematical measures of societal polarisation
• Visualizing probabilistic models in Minkowski space with intensive symmetrized Kullback-Leibler embedding
• Generalization of Clustering Agreements and Distances for Overlapping Clusters and Network Communities
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• On $f$-divergences between Cauchy distributions
• Strongly Convex Divergences
• A note on Onicescu's informational energy and correlation coefficient in exponential families
• Bayesian Update with Importance Sampling: Required Sample Size
• A note on the $f$-divergences between multivariate location-scale families with either prescribed scale matrices or location parameters
• Systematic approaches to generate reversiblizations of Markov chains