The authors thank Chryssi Giannitsarou, Larry Samuelson, Felix Kubler, and two anonymous referees for useful comments. Financial support from National Science Foundation Grant No. SES-0617859 and ESRC grant RES-000-23-1152 is gratefully acknowledged. Please address correspondence to: Noah Williams, Department of Economics, University of Wisconsin–Madison, William H. Sewell Social Science Building, Room 7434, 1180 Observatory Drive, Madison, WI 53706-1393. Phone: (608) 263-3864. E-mail: firstname.lastname@example.org.
GENERALIZED STOCHASTIC GRADIENT LEARNING*
Article first published online: 24 FEB 2010
© (2010) by the Economics Department of the University of Pennsylvania and the Osaka University Institute of Social and Economic Research Association
International Economic Review
Volume 51, Issue 1, pages 237–262, February 2010
How to Cite
Evans, . G. W., Honkapohja, S. and Williams, N. (2010), GENERALIZED STOCHASTIC GRADIENT LEARNING. International Economic Review, 51: 237–262. doi: 10.1111/j.1468-2354.2009.00578.x
Manuscript received September 2006; revised May 2008.
- Issue published online: 24 FEB 2010
- Article first published online: 24 FEB 2010
We study the properties of the generalized stochastic gradient (GSG) learning in forward-looking models. GSG algorithms are a natural and convenient way to model learning when agents allow for parameter drift or robustness to parameter uncertainty in their beliefs. The conditions for convergence of GSG learning to a rational expectations equilibrium are distinct from but related to the well-known stability conditions for least squares learning.