Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Mutual Information for the Stochastic Block Model by the Adaptive Interpolation Method
 
conference paper

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

Barbier, Jean  
•
Chan, Chun Lam  
•
Macris, Nicolas  
January 1, 2019
2019 Ieee International Symposium On Information Theory (Isit)
IEEE International Symposium on Information Theory (ISIT)

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.

  • Details
  • Metrics
Type
conference paper
DOI
10.1109/ISIT.2019.8849642
Web of Science ID

WOS:000489100300082

Author(s)
Barbier, Jean  
Chan, Chun Lam  
Macris, Nicolas  
Date Issued

2019-01-01

Publisher

IEEE

Publisher place

New York

Published in
2019 Ieee International Symposium On Information Theory (Isit)
ISBN of the book

978-1-5386-9291-2

Series title/Series vol.

IEEE International Symposium on Information Theory

Start page

405

End page

409

Subjects

Computer Science, Information Systems

•

Computer Science, Theory & Methods

•

Computer Science

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
LTHC  
Event nameEvent placeEvent date
IEEE International Symposium on Information Theory (ISIT)

Paris, FRANCE

Jul 07-12, 2019

Available on Infoscience
October 27, 2019
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/162387
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés