A Unified Approach to Aitchison’s, Dually Affine, and Transport Geometries of the Probability Simplex

A critical processing step for AI algorithms is mapping the raw data to a landscape where the similarity of two data points is conveniently defined. Frequently, when the data points are compositions of probability functions, the similarity is reduced to affine geometric concepts; the basic notion is...

Full description

Saved in:
Bibliographic Details
Main Authors: Giovanni Pistone, Muhammad Shoaib
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Axioms
Subjects:
Online Access:https://www.mdpi.com/2075-1680/13/12/823
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A critical processing step for AI algorithms is mapping the raw data to a landscape where the similarity of two data points is conveniently defined. Frequently, when the data points are compositions of probability functions, the similarity is reduced to affine geometric concepts; the basic notion is that of the straight line connecting two data points, defined as a zero-acceleration line segment. This paper provides an axiomatic presentation of the probability simplex’s most commonly used affine geometries. One result is a coherent presentation of gradient flow in Aichinson’s compositional data, Amari’s information geometry, the Kantorivich distance, and the Lagrangian optimization of the probability simplex.
ISSN:2075-1680