Mutual Information for the Stochastic Block Model by the Adaptive Interpolation Method

We rigorously derive a single-letter variational expression for the mutual information of the asymmetric two-groups stochastic block model in the dense graph regime. Existing proofs in the literature are indirect, as they involve mapping the model to a rank-one matrix estimation problem whose mutual information is then determined by a combination of methods (e.g., interpolation, cavity, algorithmic, spatial coupling). In this contribution we provide a self-contained direct method using only the recently introduced adaptive interpolation method.


Published in:
2019 Ieee International Symposium On Information Theory (Isit), 405-409
Presented at:
IEEE International Symposium on Information Theory (ISIT), Paris, FRANCE, Jul 07-12, 2019
Year:
Jan 01 2019
Publisher:
New York, IEEE
ISBN:
978-1-5386-9291-2




 Record created 2019-10-27, last modified 2019-10-28


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)