A general analysis of boundedly rational learning in social networks

We analyze boundedly rational learning in social networks within binary action environments. We establish how learning outcomes depend on the environment (i.e., informational structure, utility function), the axioms imposed on the updating behavior, and the network structure. In particular, we provi...

Full description

Bibliographic Details
Authors: Mueller-Frank, M. (Manuel)|||/items/eebf6adb-8bcb-459e-b3ff-982b47884409, Neri, C. (Claudia)|||/items/7c14a019-cf16-44ea-96f7-227b1ae379de
Format: article
Publication Date:2021
Country:España
Institution:Universidad de Navarra
Repository:Dadun. Depósito Académico Digital de la Universidad de Navarra
Language:English
OAI Identifier:oai:dadun.unav.edu:10171/69271
Online Access:https://hdl.handle.net/10171/69271
Access Level:Open access
Keyword:Social networks
Naïve inference
Naïve learning
Bounded rationality
Consensus
Information aggregation
id ES_8395c2b3ee5def3122de0a5ee4e9b822
oai_identifier_str oai:dadun.unav.edu:10171/69271
network_acronym_str ES
network_name_str España
repository_id_str
spelling A general analysis of boundedly rational learning in social networksMueller-Frank, M. (Manuel)|||/items/eebf6adb-8bcb-459e-b3ff-982b47884409Neri, C. (Claudia)|||/items/7c14a019-cf16-44ea-96f7-227b1ae379deSocial networksNaïve inferenceNaïve learningBounded rationalityConsensusInformation aggregationWe analyze boundedly rational learning in social networks within binary action environments. We establish how learning outcomes depend on the environment (i.e., informational structure, utility function), the axioms imposed on the updating behavior, and the network structure. In particular, we provide a normative foundation for quasi-Bayesian updating, where a quasi-Bayesian agent treats others' actions as if they were based only on their private signal. Quasi-Bayesian updating induces learning (i.e., convergence to the optimal action for every agent in every connected network) only in highly asymmetric environments. In all other environments, learning fails in networks with a diameter larger than 4. Finally, we consider a richer class of updating behavior that allows for nonstationarity and differential treatment of neighbors' actions depending on their position in the network. We show that within this class there exist updating systems that induce learning for most networks.WileyDadun. Depósito Académico Digital Universidad de Navarra20242024-03-2020212021-01-1920212021-01-19journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10171/69271reponame:Dadun. Depósito Académico Digital de la Universidad de Navarrainstname:Universidad de NavarraInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:dadun.unav.edu:10171/692712026-06-21T12:47:57Z
dc.title.none.fl_str_mv A general analysis of boundedly rational learning in social networks
title A general analysis of boundedly rational learning in social networks
spellingShingle A general analysis of boundedly rational learning in social networks
Mueller-Frank, M. (Manuel)|||/items/eebf6adb-8bcb-459e-b3ff-982b47884409
Social networks
Naïve inference
Naïve learning
Bounded rationality
Consensus
Information aggregation
title_short A general analysis of boundedly rational learning in social networks
title_full A general analysis of boundedly rational learning in social networks
title_fullStr A general analysis of boundedly rational learning in social networks
title_full_unstemmed A general analysis of boundedly rational learning in social networks
title_sort A general analysis of boundedly rational learning in social networks
dc.creator.none.fl_str_mv Mueller-Frank, M. (Manuel)|||/items/eebf6adb-8bcb-459e-b3ff-982b47884409
Neri, C. (Claudia)|||/items/7c14a019-cf16-44ea-96f7-227b1ae379de
author Mueller-Frank, M. (Manuel)|||/items/eebf6adb-8bcb-459e-b3ff-982b47884409
author_facet Mueller-Frank, M. (Manuel)|||/items/eebf6adb-8bcb-459e-b3ff-982b47884409
Neri, C. (Claudia)|||/items/7c14a019-cf16-44ea-96f7-227b1ae379de
author_role author
author2 Neri, C. (Claudia)|||/items/7c14a019-cf16-44ea-96f7-227b1ae379de
author2_role author
dc.contributor.none.fl_str_mv Dadun. Depósito Académico Digital Universidad de Navarra
dc.subject.none.fl_str_mv Social networks
Naïve inference
Naïve learning
Bounded rationality
Consensus
Information aggregation
topic Social networks
Naïve inference
Naïve learning
Bounded rationality
Consensus
Information aggregation
description We analyze boundedly rational learning in social networks within binary action environments. We establish how learning outcomes depend on the environment (i.e., informational structure, utility function), the axioms imposed on the updating behavior, and the network structure. In particular, we provide a normative foundation for quasi-Bayesian updating, where a quasi-Bayesian agent treats others' actions as if they were based only on their private signal. Quasi-Bayesian updating induces learning (i.e., convergence to the optimal action for every agent in every connected network) only in highly asymmetric environments. In all other environments, learning fails in networks with a diameter larger than 4. Finally, we consider a richer class of updating behavior that allows for nonstationarity and differential treatment of neighbors' actions depending on their position in the network. We show that within this class there exist updating systems that induce learning for most networks.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-01-19
2021
2021-01-19
2024
2024-03-20
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10171/69271
url https://hdl.handle.net/10171/69271
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Wiley
publisher.none.fl_str_mv Wiley
dc.source.none.fl_str_mv reponame:Dadun. Depósito Académico Digital de la Universidad de Navarra
instname:Universidad de Navarra
instname_str Universidad de Navarra
reponame_str Dadun. Depósito Académico Digital de la Universidad de Navarra
collection Dadun. Depósito Académico Digital de la Universidad de Navarra
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412146672041984
score 15,301603

Similar Items