Repository logo
 

An operational information decomposition via synergistic disclosure

Published version
Peer-reviewed

Change log

Authors

Barrett, Adam B 

Abstract

Abstract: Multivariate information decompositions hold promise to yield insight into complex systems, and stand out for their ability to identify synergistic phenomena. However, the adoption of these approaches has been hindered by there being multiple possible decompositions, and no precise guidance for preferring one over the others. At the heart of this disagreement lies the absence of a clear operational interpretation of what synergistic information is. Here we fill this gap by proposing a new information decomposition based on a novel operationalisation of informational synergy, which leverages recent developments in the literature of data privacy. Our decomposition is defined for any number of information sources, and its atoms can be calculated using elementary optimisation techniques. The decomposition provides a natural coarse-graining that scales gracefully with the system’s size, and is applicable in a wide range of scenarios of practical interest.

Description

Keywords

Paper, Statistical physics, complex systems, synergy, information theory, high-order statistics, partial information decomposition

Journal Title

Journal of Physics A: Mathematical and Theoretical

Conference Name

Journal ISSN

1751-8113
1751-8121

Volume Title

53

Publisher

IOP Publishing