From Agreement to Asymptotic Learning
Statistics Theory
2012-11-14 v5 Statistics Theory
Abstract
We consider a group of Bayesian agents who are each given an independent signal about an unknown state of the world, and proceed to communicate with each other. We study the question of asymptotic learning: do agents learn the state of the world with probability that approaches one as the number of agents tends to infinity? We show that under general conditions asymptotic learning follows from agreement on posterior actions or posterior beliefs, regardless of the communication dynamics. In particular, we prove that asymptotic learning holds for the Gale-Kariv model on undirected networks and non-atomic private beliefs.
Keywords
Cite
@article{arxiv.1105.4765,
title = {From Agreement to Asymptotic Learning},
author = {Elchanan Mossel and Allan Sly and Omer Tamuz},
journal= {arXiv preprint arXiv:1105.4765},
year = {2012}
}
Comments
This paper has been split into two: http://arxiv.org/abs/1207.5893 and http://arxiv.org/abs/1207.5895