Social learning and distributed hypothesis testing

Anusha Lalitha; Anand Sarwate; Tara Javidi

doi:https://doi.org/10.1109/ISIT.2014.6874893

Social learning and distributed hypothesis testing

Anusha Lalitha, Anand Sarwate, Tara Javidi

Rutgers, The State University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

38 Scopus citations

Abstract

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 language	English (US)
Title of host publication	2014 IEEE International Symposium on Information Theory, ISIT 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	551-555
Number of pages	5
ISBN (Print)	9781479951864
DOIs	https://doi.org/10.1109/ISIT.2014.6874893
State	Published - 2014
Event	2014 IEEE International Symposium on Information Theory, ISIT 2014 - Honolulu, HI, United States Duration: Jun 29 2014 → Jul 4 2014

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings

Other

Other	2014 IEEE International Symposium on Information Theory, ISIT 2014
Country/Territory	United States
City	Honolulu, HI
Period	6/29/14 → 7/4/14

ASJC Scopus subject areas

Theoretical Computer Science
Information Systems
Modeling and Simulation
Applied Mathematics

Access to Document

https://doi.org/10.1109/ISIT.2014.6874893

Cite this

@inproceedings{500e2d2d1046449a82c8857a69ebe452,

title = "Social learning and distributed hypothesis testing",

abstract = "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.",

author = "Anusha Lalitha and Anand Sarwate and Tara Javidi",

year = "2014",

doi = "https://doi.org/10.1109/ISIT.2014.6874893",

language = "English (US)",

isbn = "9781479951864",

series = "IEEE International Symposium on Information Theory - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "551--555",

booktitle = "2014 IEEE International Symposium on Information Theory, ISIT 2014",

address = "United States",

note = "2014 IEEE International Symposium on Information Theory, ISIT 2014 ; Conference date: 29-06-2014 Through 04-07-2014",

}

Lalitha, A, Sarwate, A & Javidi, T 2014, Social learning and distributed hypothesis testing. in 2014 IEEE International Symposium on Information Theory, ISIT 2014., 6874893, IEEE International Symposium on Information Theory - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 551-555, 2014 IEEE International Symposium on Information Theory, ISIT 2014, Honolulu, HI, United States, 6/29/14. https://doi.org/10.1109/ISIT.2014.6874893

Social learning and distributed hypothesis testing. / Lalitha, Anusha; Sarwate, Anand; Javidi, Tara.

2014 IEEE International Symposium on Information Theory, ISIT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 551-555 6874893 (IEEE International Symposium on Information Theory - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Social learning and distributed hypothesis testing

AU - Lalitha, Anusha

AU - Sarwate, Anand

AU - Javidi, Tara

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84906569526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906569526&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/ISIT.2014.6874893

DO - https://doi.org/10.1109/ISIT.2014.6874893

M3 - Conference contribution

SN - 9781479951864

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 551

EP - 555

BT - 2014 IEEE International Symposium on Information Theory, ISIT 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE International Symposium on Information Theory, ISIT 2014

Y2 - 29 June 2014 through 4 July 2014

ER -

Social learning and distributed hypothesis testing

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this