Skip to Content
You are currently on the new version of our website. Access the old version .
StatsStats
  • Article
  • Open Access

21 March 2025

19 Pages

Affine Calculus for Constrained Minima of the Kullback–Leibler Divergence

1
De Castro Statistics, Collegio Carlo Alberto, 10122 Torino, Italy
2
Nuovo SEFIR, c/o Coworld, Centro Direzionale Milano Due, Palazzo Canova, 20054 Segrate, Italy

Abstract

The non-parametric version of Amari’s dually affine Information Geometry provides a practical calculus to perform computations of interest in statistical machine learning. The method uses the notion of a statistical bundle, a mathematical structure that includes both probability densities and random variables to capture the spirit of Fisherian statistics. We focus on computations involving a constrained minimization of the Kullback–Leibler divergence. We show how to obtain neat and principled versions of known computations in applications such as mean-field approximation, adversarial generative models, and variational Bayes.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.