Learning under social influence

Alireza Tahbaz-Salehi; Alvaro Sandroni; Ali Jadbabaie

doi:10.1109/CDC.2009.5399751

Learning under social influence

Alireza Tahbaz-Salehi^*, Alvaro Sandroni, Ali Jadbabaie

^*Corresponding author for this work

Managerial Economics, Decision Sciences and Operations

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

10 Scopus citations

Abstract

In this paper, we study a model of social learning where individuals are under influence of others in their social clique. In our model, each agent receives private noisy signals about an unobservable, underlying state of the world. At the end of each time period, the belief of an individual is equal to the convex combination of her posterior beliefs derived from the signal observed, and the priors of her neighbors. Our model reduces to the well-known consensus model when private signals are non-informative. We show that if the network of social influences is strongly connected, then all agents will have asymptotically correct forecasts. In other words, all individuals will be able to asymptotically learn the true state of the world, as far as their observations are concerned. Finally, we show that all agents assign asymptotically equal beliefs to the true state of the world.

Original language	English (US)
Title of host publication	Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009
Pages	1513-1519
Number of pages	7
DOIs	https://doi.org/10.1109/CDC.2009.5399751
State	Published - Dec 1 2009
Event	48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 - Shanghai, China Duration: Dec 15 2009 → Dec 18 2009

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
ISSN (Print)	0191-2216

Other

Other	48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009
Country	China
City	Shanghai
Period	12/15/09 → 12/18/09

ASJC Scopus subject areas

Control and Systems Engineering
Modeling and Simulation
Control and Optimization

Access to Document

10.1109/CDC.2009.5399751

Fingerprint Dive into the research topics of 'Learning under social influence'. Together they form a unique fingerprint.

Cite this

@inproceedings{b6810b9f37154bba80592d810a16053d,

title = "Learning under social influence",

abstract = "In this paper, we study a model of social learning where individuals are under influence of others in their social clique. In our model, each agent receives private noisy signals about an unobservable, underlying state of the world. At the end of each time period, the belief of an individual is equal to the convex combination of her posterior beliefs derived from the signal observed, and the priors of her neighbors. Our model reduces to the well-known consensus model when private signals are non-informative. We show that if the network of social influences is strongly connected, then all agents will have asymptotically correct forecasts. In other words, all individuals will be able to asymptotically learn the true state of the world, as far as their observations are concerned. Finally, we show that all agents assign asymptotically equal beliefs to the true state of the world.",

author = "Alireza Tahbaz-Salehi and Alvaro Sandroni and Ali Jadbabaie",

year = "2009",

month = dec,

day = "1",

doi = "10.1109/CDC.2009.5399751",

language = "English (US)",

isbn = "9781424438716",

series = "Proceedings of the IEEE Conference on Decision and Control",

pages = "1513--1519",

booktitle = "Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009",

note = "48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 ; Conference date: 15-12-2009 Through 18-12-2009",

}

Tahbaz-Salehi, A , Sandroni, A & Jadbabaie, A 2009, Learning under social influence. in Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009., 5399751, Proceedings of the IEEE Conference on Decision and Control, pp. 1513-1519, 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009, Shanghai, China, 12/15/09. https://doi.org/10.1109/CDC.2009.5399751

Learning under social influence. / Tahbaz-Salehi, Alireza ; Sandroni, Alvaro; Jadbabaie, Ali.

Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009. 2009. p. 1513-1519 5399751 (Proceedings of the IEEE Conference on Decision and Control).

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

TY - GEN

T1 - Learning under social influence

AU - Tahbaz-Salehi, Alireza

AU - Sandroni, Alvaro

AU - Jadbabaie, Ali

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In this paper, we study a model of social learning where individuals are under influence of others in their social clique. In our model, each agent receives private noisy signals about an unobservable, underlying state of the world. At the end of each time period, the belief of an individual is equal to the convex combination of her posterior beliefs derived from the signal observed, and the priors of her neighbors. Our model reduces to the well-known consensus model when private signals are non-informative. We show that if the network of social influences is strongly connected, then all agents will have asymptotically correct forecasts. In other words, all individuals will be able to asymptotically learn the true state of the world, as far as their observations are concerned. Finally, we show that all agents assign asymptotically equal beliefs to the true state of the world.

AB - In this paper, we study a model of social learning where individuals are under influence of others in their social clique. In our model, each agent receives private noisy signals about an unobservable, underlying state of the world. At the end of each time period, the belief of an individual is equal to the convex combination of her posterior beliefs derived from the signal observed, and the priors of her neighbors. Our model reduces to the well-known consensus model when private signals are non-informative. We show that if the network of social influences is strongly connected, then all agents will have asymptotically correct forecasts. In other words, all individuals will be able to asymptotically learn the true state of the world, as far as their observations are concerned. Finally, we show that all agents assign asymptotically equal beliefs to the true state of the world.

UR - http://www.scopus.com/inward/record.url?scp=77950842814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950842814&partnerID=8YFLogxK

U2 - 10.1109/CDC.2009.5399751

DO - 10.1109/CDC.2009.5399751

M3 - Conference contribution

AN - SCOPUS:77950842814

SN - 9781424438716

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 1513

EP - 1519

BT - Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009

T2 - 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009

Y2 - 15 December 2009 through 18 December 2009

ER -