Generalized Stochastic Gradient Learning
We study the properties of generalized stochastic gradient (GSG) learning in forward-looking models. We examine how the conditions for stability of standard stochastic gradient (SG) learning both differ from and are related to E-stability, which governs stability under least squares learning. SG algorithms are sensitive to units of measurement and we show that there is a transformation of variables for which E-stability governs SG stability. GSG algorithms with constant gain have a deeper justification in terms of parameter drift, robustness and risk sensitivity.
|Date of creation:||Oct 2005|
|Date of revision:|
|Contact details of provider:|| Postal: National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.|
Web page: http://www.nber.org
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- George W. Evans & Seppo Honkapohja, 2001.
"Expectations and the Stability Problem for Optimal Monetary Policies,"
University of Oregon Economics Department Working Papers
2001-6, University of Oregon Economics Department, revised 03 Aug 2001.
- George W. Evans & Seppo Honkapohja, 2003. "Expectations and the Stability Problem for Optimal Monetary Policies," Review of Economic Studies, Oxford University Press, vol. 70(4), pages 807-824.
- Honkapohja, Seppo & Evans, George W., 2000. "Expectations and the stability problem for optimal monetary policies," Discussion Paper Series 1: Economic Studies 2000,10, Deutsche Bundesbank, Research Centre.
- Evans, George W. & Honkapohja, Seppo, 2001. "Expectations and the Stability Problem for Optimal Monetary Policies," CEPR Discussion Papers 2805, C.E.P.R. Discussion Papers.
- Honkapohja, S. & Evans, G.W., 2000. "Expectations and the Stability Problem for Optimal Monetary Policies," University of Helsinki, Department of Economics 481, Department of Economics.
- Evans, George W. & Honkapohja, S., 1998.
"Stochastic gradient learning in the cobweb model,"
Elsevier, vol. 61(3), pages 333-337, December.
When requesting a correction, please mention this item's handle: RePEc:nbr:nberte:0317. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ()
If references are entirely missing, you can add them using this form.