Information Decomposition Based on Cooperative Game Theory

Ay, Nihat, Polani, Daniel and Virgo, Nathaniel (2020) Information Decomposition Based on Cooperative Game Theory. Kybernetika, 56 (5). pp. 979-1014. ISSN 0023-5954
Copy

We offer a new approach to the information decomposition problem in information theory: given a ‘target’ random variable co-distributed with multiple ‘source’ variables, how can we decompose the mutual information into a sum of non-negative terms that quantify the contributions of each random variable, not only individually but also in combination? We derive our composition from cooperative game theory. It can be seen as assigning a “fair share” of the mutual information to each combination of the source variables. Our decomposition is based on a different lattice from the usual ‘partial information decomposition’ (PID) approach, and as a consequence our decomposition has a smaller number of terms: it has analogs of the synergy and unique information terms, but lacks terms cor- responding to redundancy. Because of this, it is able to obey equivalents of the axioms known as ‘local positivity’ and ‘identity’, which cannot be simultaneously satisfied by a PID measure.


picture_as_pdf
Inf_Decomp_27_Sep_NA_Submission_Kybernetika.pdf
subject
Published Version
copyright
Available under Unspecified

View Download
visibility_off picture_as_pdf

Draft Version
lock

Atom BibTeX OpenURL ContextObject in Span OpenURL ContextObject Dublin Core MPEG-21 DIDL Data Cite XML EndNote HTML Citation METS MODS RIOXX2 XML Reference Manager Refer ASCII Citation
Export

Downloads