Quantifying Redundant Information in Predicting a Target Random Variable
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Exact common information2014
- Quantifying Synergistic Mutual Information2014
- Towards a synergy-based approach to measuring information modification2013
- Bivariate measure of redundant informationPhysical Review E, 2013
- Shared Information—New Insights and Problems in Decomposing Information in Complex Systems2013
- Integrated Information in Discrete Dynamical Systems: Motivation and Theoretical FrameworkPLOS Computational Biology, 2008
- Computational analysis of the synergy among multiple interacting genesMolecular Systems Biology, 2007
- Network Information and Connected CorrelationsPhysical Review Letters, 2003
- Decoding neuronal spike trains: How important are correlations?Proceedings of the National Academy of Sciences, 2003
- The common information of two dependent random variablesIEEE Transactions on Information Theory, 1975