License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.STACS.2021.24
URN: urn:nbn:de:0030-drops-136692
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2021/13669/
Go to the corresponding LIPIcs Volume Portal


Coja-Oghlan, Amin ; Hahn-Klimroth, Max ; Loick, Philipp ; Müller, Noela ; Panagiotou, Konstantinos ; Pasch, Matija

Inference and Mutual Information on Random Factor Graphs

pdf-format:
LIPIcs-STACS-2021-24.pdf (0.7 MB)


Abstract

Random factor graphs provide a powerful framework for the study of inference problems such as decoding problems or the stochastic block model. Information-theoretically the key quantity of interest is the mutual information between the observed factor graph and the underlying ground truth around which the factor graph was created; in the stochastic block model, this would be the planted partition. The mutual information gauges whether and how well the ground truth can be inferred from the observable data. For a very general model of random factor graphs we verify a formula for the mutual information predicted by physics techniques. As an application we prove a conjecture about low-density generator matrix codes from [Montanari: IEEE Transactions on Information Theory 2005]. Further applications include phase transitions of the stochastic block model and the mixed k-spin model from physics.

BibTeX - Entry

@InProceedings{cojaoghlan_et_al:LIPIcs.STACS.2021.24,
  author =	{Coja-Oghlan, Amin and Hahn-Klimroth, Max and Loick, Philipp and M\"{u}ller, Noela and Panagiotou, Konstantinos and Pasch, Matija},
  title =	{{Inference and Mutual Information on Random Factor Graphs}},
  booktitle =	{38th International Symposium on Theoretical Aspects of Computer Science (STACS 2021)},
  pages =	{24:1--24:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-180-1},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{187},
  editor =	{Bl\"{a}ser, Markus and Monmege, Benjamin},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/13669},
  URN =		{urn:nbn:de:0030-drops-136692},
  doi =		{10.4230/LIPIcs.STACS.2021.24},
  annote =	{Keywords: Information theory, random factor graphs, inference problems, phase transitions}
}

Keywords: Information theory, random factor graphs, inference problems, phase transitions
Collection: 38th International Symposium on Theoretical Aspects of Computer Science (STACS 2021)
Issue Date: 2021
Date of publication: 10.03.2021


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI