Learning and convergence in networks
Opolot, Daniel and Azomahou, Théophile T. (2012). Learning and convergence in networks. UNU-MERIT.
Document type:
Report
Collection:
-
Attached Files (Some files may be inaccessible until you login with your UNU Collections credentials) Name Description MIMEType Size Downloads wp2012-074.pdf PDF application/pdf 868.53KB -
Author Opolot, Daniel
Azomahou, Théophile T.Title Learning and convergence in networks Publication Date 2012 Publisher UNU-MERIT Abstract We study the convergence properties of learning in social and economic networks. We characterize the effect of network structure on the long-run convergent behaviour and on the time of convergence to steady state. Agents play a repeated game governed by two underlying behavioural rules; they are myopic and boundedly rational. Under this setup, the long-run limit of the adoptive process converges to a unique equilibrium. We treat the dynamic process as a Markov chain and derive the bound for the convergence time of the chain in terms of the stationary distribution of the initial and steady state population configurations, and the spectrum of the transition matrix. We in turn differentiate between the two antagonistic effects of the topology of the interaction structure on the convergence time; that through the initial state and that through the asymptotic behaviour. The effect through the initial state favours local interactions and sparsely connected network structures, while that through the asymptotic behaviour favours densely and uniformly connected network structures. The main result is that the most efficient network topologies for faster convergence or learning are those where agents belong to subgroups in which the inter-subgroup interactions are "weaker" relative to within subgroup interactions. We further show that the inter-subgroup interactions or long-ties should not be "too weak" lest the convergence time be infinitely long and hence slow learning. Keyword Learning
Local interactions
Coordination game
Strategic complementarity
Convergence time
Convergence rate
Markov chainJEL C73
D83Copyright Holder UNU-MERIT Copyright Year 2012 -
Citation counts Search Google Scholar Access Statistics: 790 Abstract Views, 135 File Downloads - Detailed Statistics Created: Wed, 11 Dec 2013, 17:14:19 JST