Quantifying Redundant Information in Predicting a Target Random Variable

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.

6 pages, 6 figures

References in corpus (1)

• Nonnegative Decomposition of Multivariate Information

Cited by in corpus (12)

• Measuring multivariate redundant information with pointwise common change in surprisal
• Pointwise Partial Information Decomposition using the Specificity and Ambiguity Lattices
• Decomposing causality into its synergistic, unique, and redundant components
• A Novel Approach to the Partial Information Decomposition
• Generalised Measures of Multivariate Information Content
• Synergy, Redundancy and Common Information
• Orders between channels and implications for partial information decomposition
• A Measure of Synergy based on Union Information
• On shared and multiple information
• Explicit Formula for Partial Information Decomposition
• Partial information decomposition: redundancy as information bottleneck
• An Approximation Scheme for Multivariate Information based on Partial Information Decomposition