Quantifying Redundant Information in Predicting a Target Random Variable

TL;DR

This paper explores how to measure the amount of shared information among multiple variables about a target, proposing new measures that satisfy certain desirable properties.

Contribution

It introduces novel measures of redundant information that better capture common information about a target variable.

Findings

Proposed measures satisfy key properties of redundancy

Compared new measures with existing ones

Demonstrated effectiveness in theoretical scenarios

Abstract

This paper considers the problem of defining a measure of redundant information that quantifies how much common information two or more random variables specify about a target random variable. We discussed desired properties of such a measure, and propose new measures with some desirable properties.