2000 character limit reached
Quantifying High-order Interdependencies via Multivariate Extensions of the Mutual Information (1902.11239v1)
Published 28 Feb 2019 in cs.IT, math.IT, and q-bio.NC
Abstract: This article introduces a model-agnostic approach to study statistical synergy, a form of emergence in which patterns at large scales are not traceable from lower scales. Our framework leverages various multivariate extensions of Shannon's mutual information, and introduces the O-information as a metric capable of characterising synergy- and redundancy-dominated systems. We develop key analytical properties of the O-information, and study how it relates to other metrics of high-order interactions from the statistical mechanics and neuroscience literature. Finally, as a proof of concept, we use the proposed framework to explore the relevance of statistical synergy in Baroque music scores.