Generalized Stochastic Gradient Learning
26 Pages Posted: 1 Mar 2010
There are 3 versions of this paper
Generalized Stochastic Gradient Learning
Generalized Stochastic Gradient Learning
Abstract
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.
Suggested Citation: Suggested Citation
Do you have a job opening that you would like to promote on SSRN?
Recommended Papers
-
Social Learning and Monetary Policy Rules
By Jasmina Arifovic, James Bullard, ...
-
Imperfect Knowledge, Inflation Expectations, and Monetary Policy
-
Imperfect Knowledge, Inflation Expectations, and Monetary Policy
-
Expectations and the Stability Problem for Optimal Monetary Policies
By George W. Evans and Seppo Honkapohja
-
Expectations and the Stability Problem for Optimal Monetary Policies
By George W. Evans and Seppo Honkapohja
-
Expectations and the Stability Problem for Optimal Monetary Policies
By George W. Evans and Seppo Honkapohja