Social Learning in a Changing World
We study a model of learning on social networks in dynamic environments, describing a group of agents who are each trying to estimate an underlying state that varies over time, given access to weak signals and the estimates of their social network neighbors.
We study three models of agent behavior. In the fixed response model, agents use a fixed linear combination to incorporate information from their peers into their own estimate. This can be thought of as an extension of the DeGroot model to a dynamic setting. In the best response model, players calculate minimum variance linear estimators of the underlying state.
We show that regardless of the initial configuration, fixed response dynamics converge to a steady state, and that the same holds for best response on the complete graph. We show that best response dynamics can, in the long term, lead to estimators with higher variance than is achievable using well chosen fixed responses.
The penultimate prediction model is an elaboration of the best response model. While this model only slightly complicates the computations required of the agents, we show that in some cases it greatly increases the efficiency of learning, and on complete graphs is in fact optimal, in a strong sense.
Keywordssocial networks Bayesian agents social learning
Unable to display preview. Download preview PDF.
- 1.Aaronson, S.: The complexity of agreement. In: Proceedings of the Thirty-Seventh Annual ACM Symposium on Theory of Computing, STOC 2005, pp. 634–643. ACM (2005)Google Scholar
- 2.Acemoglu, D., Dahleh, M., Lobel, I., Ozdaglar, A.: Bayesian learning in social networks (2008)Google Scholar
- 3.Acemoglu, D., Nedic, A., Ozdaglar, A.: Convergence of rule-of-thumb learning rules in social networks. In: 47th IEEE Conference on Decision and Control, CDC 2008, pp. 1714–1720. IEEE (2008)Google Scholar
- 5.Bachelier, L.: Théorie de la spéculation. Gauthier-Villars (1900)Google Scholar
- 6.Bala, V., Goyal, S.: Learning from neighbours. Review of Economic Studies 65(3), 595–621 (1998), http://ideas.repec.org/a/bla/restud/v65y1998i3p595-621.html CrossRefMATHGoogle Scholar
- 8.Besley, T., Case, A.: Diffusion as a learning process: Evidence from hyv cotton (1994) Working PapersGoogle Scholar
- 10.DeGroot, M.H.: Reaching a consensus. Journal of the American Statistical Association, 118–121 (1974)Google Scholar
- 12.Frongillo, R.M., Schoenebeck, G., Tamuz, O.: Social learning in a changing world. Tech. rep. (September 2011), http://arxiv.org/abs/1109.5482
- 13.Gale, D., Kariv, S.: Bayesian learning in social networks. Games and Economic Behavior 45(2), 329–346 (2003), http://ideas.repec.org/a/eee/gamebe/v45y2003i2p329-346.html MathSciNetCrossRefMATHGoogle Scholar
- 14.Geanakoplos, J.: Common knowledge. In: Proceedings of the 4th Conference on Theoretical Aspects of Reasoning about Knowledge, pp. 254–315. Morgan Kaufmann Publishers Inc. (1992)Google Scholar
- 16.Jackson, M.O.: The economics of social networks. In: Blundell, R., Newey, W., Persson, T. (eds.) Theory and Applications: Ninth World Congress of the Econometric Society. Advances in Economics and Econometrics, vol. I, pp. 1–56. Cambridge University Press (2006)Google Scholar
- 17.Jadbabaie, A., Sandroni, A., Tahbaz-Salehi, A.: Non-bayesian social learning, second version. Pier working paper archive, Penn Institute for Economic Research, Department of Economics. University of Pennsylvania (2010)Google Scholar
- 20.McKelvey, R.D., Page, T.: Common knowledge, consensus, and aggregate information. Econometrica: Journal of the Econometric Society, 109–127 (1986)Google Scholar
- 21.Mossel, E., Tamuz, O.: Efficient bayesian learning in social networks with gaussian estimators. Tech. rep. (September 2010), http://arxiv.org/abs/1002.0747
- 24.Simon, H.: Reason in Human Affairs. Stanford University Press (1982)Google Scholar