On Information (pseudo) Metric
Probability
2021-03-04 v1 Information Theory
math.IT
Neurons and Cognition
Machine Learning
Abstract
This short note revisit information metric, underlining that it is a pseudo metric on manifolds of observables (random variables), rather than as usual on probability laws. Geodesics are characterized in terms of their boundaries and conditional independence condition. Pythagorean theorem is given, providing in special case potentially interesting natural integer triplets. This metric is computed for illustration on Diabetes dataset using infotopo package.
Cite
@article{arxiv.2103.02008,
title = {On Information (pseudo) Metric},
author = {Pierre Baudot},
journal= {arXiv preprint arXiv:2103.02008},
year = {2021}
}