The Basics of Information Geometry

TL;DR

This paper introduces the fundamental concepts of information geometry, focusing on measuring the distinguishability between probability distributions through the notion of 'distance' in a geometric framework.

Contribution

It provides an accessible overview of the basic ideas and mathematical tools used to quantify differences between probability distributions in information geometry.

Findings

Introduces the concept of 'distance' between probability distributions.

Explores the geometric structure underlying probability spaces.

Provides foundational understanding for further study in information geometry.

Abstract

To what extent can we distinguish one probability distribution from another? Are there quantitative measures of distinguishability? The goal of this tutorial is to approach such questions by introducing the notion of the "distance" between two probability distributions and exploring some basic ideas of such an "information geometry".