This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

Generalized Stochastic Gradient Learning

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
George W. Evans () (University of Oregon Economics Department)
Seppo Honkapohja () (University of Cambridge)
Noah Williams (Princeton University and NBER)

Additional information is available for the following registered author(s):

Abstract

We study the properties of generalized stochastic gradient (GSG) learning in forwardlooking 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.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. In case of further problems read the IDEAS help file. Note that these files are not on the IDEAS site. Please be patient as the files may be large.

File URL: http://economics.uoregon.edu/papers/UO-2005-17_Evans_Gradient.pdf
File Format: application/pdf
File Function:
Download Restriction: no

Publisher Info
Paper provided by University of Oregon Economics Department in its series University of Oregon Economics Department Working Papers with number 2005-17.

Download reference. The following formats are available: HTML, plain text, BibTeX, RIS (EndNote), ReDIF
Length: 35
Date of creation: 19 Sep 2005
Date of revision: 18 May 2008
Handle: RePEc:ore:uoecwp:2005-17

Contact details of provider:
Postal: 1285 University of Oregon, 435 PLC, Eugene, OR 97403-1285
Phone: (541) 346-4661
Fax: (541) 346-1243
Email:
Web page: http://economics.uoregon.edu/
More information through EDIRC

For technical questions regarding this item, or to correct its listing, contact: (Bill Harbaugh).

Related research
Keywords: adaptive learning E-stability recursive least squares robust estimation

Other versions of this item:

Find related papers by JEL classification:
C62 - Mathematical and Quantitative Methods - - Mathematical Methods and Programming - - - Existence and Stability Conditions of Equilibrium
C65 - Mathematical and Quantitative Methods - - Mathematical Methods and Programming - - - Miscellaneous Mathematical Tools
D83 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Search, Learning, and Information
E10 - Macroeconomics and Monetary Economics - - General Aggregative Models - - - General
E17 - Macroeconomics and Monetary Economics - - General Aggregative Models - - - Forecasting and Simulation

This paper has been announced in the following NEP Reports:

References listed on IDEAS
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.:
  1. George W. Evans & Seppo Honkapohja, 2003. "Expectations and the Stability Problem for Optimal Monetary Policies," Review of Economic Studies, Blackwell Publishing, vol. 70(4), pages 807-824, October. [Downloadable!] (restricted)
    Other versions:
Full references

Cited by:
(explanations, 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.)

  1. Seppo Honkapohja & Kaushik Mitra, 2006. "Learning Stability in Economies with Heterogeneous Agents," Review of Economic Dynamics, Elsevier for the Society for Economic Dynamics, vol. 9(2), pages 284-309, April. [Downloadable!] (restricted)
    Other versions:
  2. James B. Bullard, 2006. "The learnability criterion and monetary policy," Review, Federal Reserve Bank of St. Louis, issue May, pages 203-217. [Downloadable!]
  3. Evans , George W & Honkapohja, Seppo, 2007. "Robust learning stability with operational monetary policy rules," Research Discussion Papers 31/2007, Bank of Finland. [Downloadable!]
    Other versions:
  4. Sergey Slobodyan & Atanas Christev, 2006. "On learnability of E–stable equilibria," Computing in Economics and Finance 2006 451, Society for Computational Economics. [Downloadable!]
  5. Emiliano Santoro & Damjan Pfajfar, 2006. "Heterogeneity and learning in inflation expectation formation: an empirical assessment," Department of Economics Working Papers 0607, Department of Economics, University of Trento, Italia. [Downloadable!]
  6. Gaetano Gaballo, 2008. "Interactive Learning and Behavioral Sunspots," Department of Economic Policy, Finance and Development (DEPFID) University of Siena 1008, Department of Economic Policy, Finance and Development (DEPFID), University of Siena. [Downloadable!]
  7. Carceles-Poveda, Eva & Giannitsarou, Chryssi, 2006. "Adaptive Learning in Practice," CEPR Discussion Papers 5627, C.E.P.R. Discussion Papers. [Downloadable!] (restricted)
    Other versions:
  8. Sergey Slobodyan & Anna Bogomolova & Dmitri Kolyuzhnov, 2006. "Stochastic Gradient versus Recursive Least Squares Learning," Computing in Economics and Finance 2006 446, Society for Computational Economics. [Downloadable!]
Statistics
Access and download statistics

Did you know? All RePEc services are meant to be be free forever, as they are all run by volunteers.

This page was last updated on 2008-11-16.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.