Asymptotic Learning on Bayesian Social Networks

Abstract

Understanding information exchange and aggregation on networks is a central problem in theoretical economics, probability and statistics. We study a standard model of economic agents on the nodes of a social network graph who learn a binary "state of the world" S, from initial signals, by repeatedly observing each other's best guesses. Asymptotic learning is said to occur on a family of graphs G_n = (V_n, E_n), with |V_n| tending to infinity, if with probability tending to 1 as n tends to infinity all agents in G_n eventually estimate S correctly. We identify sufficient conditions for asymptotic learning and contruct examples where learning does not occur when the conditions do not hold.

28 pages, 2 figures. arXiv admin note: substantial text overlap with arXiv:1105.4765

Cited by in corpus (16)

• Strategic Learning and the Topology of Social Networks
• Opinion Exchange Dynamics
• Social learning equilibria
• Distributed Learning for Cooperative Inference
• Bayesian Learning without Recall
• Learning without recall in directed circles and rooted trees
• Making Consensus Tractable
• Bayesian Decision Making in Groups is Hard
• Bayesian Heuristics for Group Decisions
• Loss of information in feedforward social networks
• Learning without Recall: A Case for Log-Linear Learning
• Decentralized Bayesian learning in dynamic games: A framework for studying informational cascades
• Averaging plus Learning Models and Their Asymptotics
• Do Informational Cascades Happen with Non-myopic Agents?
• Asynchronous Majority Dynamics in Preferential Attachment Trees
• Learning Agents in Black-Scholes Financial Markets: Consensus Dynamics and Volatility Smiles