Convergence of rule-of-thumb learning rules in social networks
- 1 January 2008
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2008 47th IEEE Conference on Decision and Control
- No. 01912216,p. 1714-1720
- https://doi.org/10.1109/cdc.2008.4739167
Abstract
We study the problem of dynamic learning by a social network of agents. Each agent receives a signal about an underlying state and communicates with a subset of agents (his neighbors) in each period. The network is connected. In contrast to the majority of existing learning models, we focus on the case where the underlying state is time-varying. We consider the following class of rule of thumb learning rules: at each period, each agent constructs his posterior as a weighted average of his prior, his signal and the information he receives from neighbors. The weights given to signals can vary over time and the weights given to neighbors can vary across agents. We distinguish between two subclasses: (1) constant weight rules; (2) diminishing weight rules. The latter reduces weights given to signals asymptotically to 0. Our main results characterize the asymptotic behavior of beliefs. We show that the general class of rules leads to unbiased estimates of the underlying state. When the underlying state has innovations with variance tending to zero asymptotically, we show that the diminishing weight rules ensure convergence in the mean-square sense. In contrast, when the underlying state has persistent innovations, constant weight rules enable us to characterize explicit bounds on the mean square error between an agent¿s belief and the underlying state as a function of the type of learning rule and signal structure.Keywords
This publication has 15 references indexed in Scilit:
- Consensus Filters for Sensor Networks and Distributed Sensor FusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Job Information Networks, Neighborhood Effects, and InequalityJournal of Economic Literature, 2004
- Consensus Problems in Networks of Agents With Switching Topology and Time-DelaysIEEE Transactions on Automatic Control, 2004
- Social learning in a heterogeneous population: technology diffusion in the Indian Green RevolutionJournal of Development Economics, 2004
- Coordination of groups of mobile autonomous agents using nearest neighbor rulesIEEE Transactions on Automatic Control, 2003
- Pathological Outcomes of Observational LearningEconometrica, 2000
- Learning from NeighboursThe Review of Economic Studies, 1998
- A Simple Model of Herd BehaviorThe Quarterly Journal of Economics, 1992
- Distributed asynchronous deterministic and stochastic gradient optimization algorithmsIEEE Transactions on Automatic Control, 1986
- The Strength of Weak TiesAmerican Journal of Sociology, 1973