A new metric for probability distributions
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A metric for probability distributions is introduced, which is bounded, information-theoretically motivated, and has a natural Bayesian interpretation, and the square root of the well-known /spl chi//sup 2/ distance is an asymptotic approximation.
Abstract
We introduce a metric for probability distributions, which is bounded, information-theoretically motivated, and has a natural Bayesian interpretation. The square root of the well-known /spl chi//sup 2/ distance is an asymptotic approximation to it. Moreover, it is a close relative of the capacitory discrimination and Jensen-Shannon divergence.