On uniform boundedness of sequential social learning

TL;DR

This paper investigates conditions under which individuals in social learning models learn uniformly quickly, introducing a new criterion and technical tools to identify information structures with bounded learning times.

Contribution

It proposes a bi-parametric criterion for information structures ensuring uniformly bounded learning times and extends existing supermartingale convergence results.

Findings

Identifies a family of information structures with fast, uniform learning.

Develops a new technical tool based on weakly active supermartingales.

Extends classical supermartingale convergence results.

Abstract

In the classical herding model, asymptotic learning refers to situations where individuals eventually take the correct action regardless of their private information. Classical results identify classes of information structures for which such learning occurs. Recent papers have argued that typically, even when asymptotic learning occurs, it takes a very long time. In this paper related questions are referred. The paper studies whether there is a natural family of information structures for which the time it takes until individuals learn is uniformly bounded from above. Indeed, we propose a simple bi-parametric criterion that defines the information structure, and on top of that compute the time by which individuals learn (with high probability) for any pair of parameters. Namely, we identify a family of information structures where individuals learn uniformly fast. The underlying technical tool we deploy is a uniform convergence result on a newly introduced class of `weakly active' supermartingales. This result extends an earlier result of Fudenberg and Levine (1992) on active supermartingales.