Social learning and distributed hypothesis testing

Anusha Lalitha, Anand Sarwate, Tara Javidi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Scopus citations


This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The distributions are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which agents first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a 'non-Bayesian' linear consensus using the log-beliefs of their neighbors. The main result of this paper is that under mild assumptions, the belief of any agent in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions.

Original languageEnglish (US)
Title of host publication2014 IEEE International Symposium on Information Theory, ISIT 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Print)9781479951864
StatePublished - 2014
Event2014 IEEE International Symposium on Information Theory, ISIT 2014 - Honolulu, HI, United States
Duration: Jun 29 2014Jul 4 2014

Publication series

NameIEEE International Symposium on Information Theory - Proceedings


Other2014 IEEE International Symposium on Information Theory, ISIT 2014
Country/TerritoryUnited States
CityHonolulu, HI

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Applied Mathematics


Dive into the research topics of 'Social learning and distributed hypothesis testing'. Together they form a unique fingerprint.

Cite this