dc.contributor.author | Lobel, Ilan | |
dc.contributor.author | Acemoglu, K. Daron | |
dc.contributor.author | Dahleh, Munther A | |
dc.contributor.author | Ozdaglar, Asuman E | |
dc.date.accessioned | 2011-02-24T15:14:01Z | |
dc.date.available | 2011-02-24T15:14:01Z | |
dc.date.issued | 2009-07 | |
dc.date.submitted | 2009-06 | |
dc.identifier.isbn | 978-1-4244-4523-3 | |
dc.identifier.issn | 0743-1619 | |
dc.identifier.other | INSPEC Accession Number: 10776036 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/61320 | |
dc.description | Author's final manuscript of an article that had the title changed during publication to "Lower Bounds on the Rate of Learning in Social Networks." Final published version available at: http://hdl.handle.net/1721.1/59971 | |
dc.description.abstract | We study the rate of convergence of Bayesian learning in
social networks. Each individual receives a signal about the
underlying state of the world, observes a subset of past actions
and chooses one of two possible actions. Our previous
work [1] established that when signals generate unbounded
likelihood ratios, there will be asymptotic learning under
mild conditions on the social network topology—in the sense
that beliefs and decisions converge (in probability) to the
correct beliefs and action. The question of the speed of
learning has not been investigated, however. In this paper, we
provide estimates of the speed of learning (the rate at which
the probability of the incorrect action converges to zero). We
focus on a special class of topologies in which individuals
observe either a random action from the past or the most
recent action. We show that convergence to the correct action
is faster than a polynomial rate when individuals observe
the most recent action and is at a logarithmic rate when
they sample a random action from the past. This suggests
that communication in social networks that lead to repeated
sampling of the same individuals lead to slower aggregation
of information. | en_US |
dc.language.iso | en_US | |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1109/ACC.2009.5160660 | en_US |
dc.rights | Attribution-Noncommercial-Share Alike 3.0 Unported | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/3.0/ | en_US |
dc.source | MIT web domain | en_US |
dc.title | Rate of Convergence of Learning in Social Networks | en_US |
dc.title.alternative | Lower Bounds on the Rate of Learning in Social Networks | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Lobel, I. et al. “Lower bounds on the rate of learning in social networks.” American Control Conference, 2009. ACC '09. 2009. 2825-2830. | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Economics | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Operations Research Center | en_US |
dc.contributor.approver | Acemoglu, Daron | |
dc.contributor.mitauthor | Lobel, Ilan | |
dc.contributor.mitauthor | Acemoglu, Daron | |
dc.contributor.mitauthor | Dahleh, Munther A. | |
dc.contributor.mitauthor | Ozdaglar, Asuman E. | |
dc.relation.journal | Proceedings of the American Control Conference, 2009 | en_US |
dc.eprint.version | Author's final manuscript | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
dspace.orderedauthors | Lobel, Ilan; Acemoglu, Daron; Dahleh, Munther; Ozdaglar, Asuman | en |
dc.identifier.orcid | https://orcid.org/0000-0002-1827-1285 | |
dc.identifier.orcid | https://orcid.org/0000-0002-1470-2148 | |
dc.identifier.orcid | https://orcid.org/0000-0003-0908-7491 | |
mit.license | OPEN_ACCESS_POLICY | en_US |
mit.metadata.status | Complete | |