Divergence Network: Graphical calculation method of divergence functions

TL;DR

This paper introduces divergence networks, a graphical method for calculating divergence functions that enhances understanding of their geometric relationships and simplifies their interpretation.

Contribution

The paper presents divergence networks as a novel graphical approach for calculating and visualizing divergence functions, improving intuition and comprehension.

Findings

Divergence networks facilitate intuitive understanding of divergence functions.

The method allows for straightforward graphical calculations of divergence.

It clarifies geometric relationships among divergence functions.

Abstract

In this paper, we introduce directed networks called `divergence network' in order to perform graphical calculation of divergence functions. By using the divergence networks, we can easily understand the geometric meaning of calculation results and grasp relations among divergence functions intuitively.