The speed of sequential asymptotic learning

DOI10.1016/J.JET.2017.11.009MaRDI QIDQ1693201zbMATH OpenOpenAlexWikidataFDO

Authors Wade Hann-Caruthers, Vadim V. Martynov, Omer Tamuz

Publication date 11 January 2018

Published in Journal of Economic Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1707.02689, https://authors.library.caltech.edu/78984/

zbMATH Keywords

herd behaviorsocial learning

Mathematics Subject Classification ID

Social networks; opinion dynamics (91D30) Rationality and learning in game theory (91A26)

Abstract: In the classical herding literature, agents receive a private signal regarding a binary state of nature, and sequentially choose an action, after observing the actions of their predecessors. When the informativeness of private signals is unbounded, it is known that agents converge to the correct action and correct belief. We study how quickly convergence occurs, and show that it happens more slowly than it does when agents observe signals. However, we also show that the speed of learning from actions can be arbitrarily close to the speed of learning from signals. In particular, the expected time until the agents stop taking the wrong action can be either finite or infinite, depending on the private signal distribution. In the canonical case of Gaussian private signals we calculate the speed of convergence precisely, and show explicitly that, in this case, learning from actions is significantly slower than learning from signals.

Recommendations

• A general analysis of sequential social learning
• Bayesian social learning with local interactions
• Bayesian learning in social networks
• Social learning with private and common values
• Bayesian learning in social networks.

Cites work

• Bayesian learning in social networks
• How Fast do Rational Agents Learn?
• Information percolation with equilibrium search dynamics
• Pathological Outcomes of Observational Learning
• The maxmin of recursive games with incomplete information on one side

Cited in

(9)

• On the role of responsiveness in rational herds
• On the asymptotic behaviour of linear learning processes with partial forgetting
• Identifiable information structures
• Fast learning rates in statistical inference through aggregation
• Learning from reviews: the selection effect and the speed of learning
• Fast rates by transferring from auxiliary hypotheses
• Quickest Search and Learning Over Correlated Sequences: Theory and Application
• How fragile are information cascades?
• Pathological Outcomes of Observational Learning

This page was built for publication: The speed of sequential asymptotic learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1693201)