Social Learning with Partial Information Sharing

TL;DR

This paper investigates how agents in social networks can learn effectively by sharing partial belief information, identifying conditions for successful hypothesis detection and revealing various convergence behaviors.

Contribution

It establishes conditions under which sharing partial beliefs suffices for accurate hypothesis testing in social networks, advancing understanding of social learning dynamics.

Findings

Conditions for effective partial belief sharing

Multiple convergence regimes identified

Agents can reliably detect hypotheses with partial info

Abstract

This work studies the learning abilities of agents sharing partial beliefs over social networks. The agents observe data that could have risen from one of several hypotheses and interact locally to decide whether the observations they are receiving have risen from a particular hypothesis of interest. To do so, we establish the conditions under which it is sufficient to share partial information about the agents' belief in relation to the hypothesis of interest. Some interesting convergence regimes arise.