Skip to main content

Gaussian Learning-Without-Recall in a dynamic social network

Author(s): Wang, C; Chazelle, Bernard

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1s67t
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, C-
dc.contributor.authorChazelle, Bernard-
dc.date.accessioned2018-07-20T15:07:05Z-
dc.date.available2018-07-20T15:07:05Z-
dc.date.issued2017-07-03en_US
dc.identifier.citationWang, C, Chazelle, B. (2017). Gaussian Learning-Without-Recall in a dynamic social network. 5109 - 5114. doi:10.23919/ACC.2017.7963747en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1s67t-
dc.description.abstractWe analyze the dynamics of the Learning-Without-Recall model with Gaussian priors in a dynamic social network. Agents seeking to learn the state of the world, the 'truth', exchange signals about their current beliefs across a changing network and update them accordingly. The agents are assumed memoryless and rational, meaning that they Bayes-update their beliefs based on current states and signals, with no other information from the past. The other assumption is that each agent hears a noisy signal from the truth at a frequency bounded away from zero. Under these conditions, we show that the system reaches truthful consensus almost surely with a convergence rate that is polynomial in expectation. Somewhat paradoxically, high out degree can slow down the learning process. The lower-bound assumption on the truth-hearing frequency is necessary: even infinitely frequent access to the truth offers no guarantee of truthful consensus in the limit.en_US
dc.format.extent5109 - 5114en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of the American Control Conferenceen_US
dc.rightsAuthor's manuscripten_US
dc.titleGaussian Learning-Without-Recall in a dynamic social networken_US
dc.typeConference Articleen_US
dc.identifier.doidoi:10.23919/ACC.2017.7963747-
dc.date.eissued2017-07-03en_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/journal-articleen_US

Files in This Item:
File Description SizeFormat 
Gaussian Learning Without Recall in a Dynamic Social Network.pdf109.73 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.