Stochastic Gradient versus Recursive Least Squares Learning

Sergey Slobodyan, Anna Bogomolova, and Dmitri Kolyuzhnov

CERGE-EI Working Papers from The Center for Economic Research and Graduate Education - Economics Institute, Prague

Abstract: In this paper, we perform an in—depth investigation of relative merits of two adaptive learning algorithms with constant gain, Recursive Least Squares (RLS) and Stochastic Gradient (SG), using the Phelps model of monetary policy as a testing ground. The behavior of the two learning algorithms is very different. Under the mean (averaged) RLS dynamics, the Self—Confirming Equilibrium (SCE) is stable for initial conditions in a very small region around the SCE. Large distance movements of perceived model parameters from their SCE values, or “escapes”, are observed. On the other hand, the SCE is stable under the SG mean dynamics in a large region. However, actual behavior of the SG learning algorithm is divergent for a wide range of constant gain parameters, including those that could be justified as economically meaningful. We explain the discrepancy by looking into the structure of eigenvalues and eigenvectors of the mean dynamics map under SG learning. Results of our paper hint that caution is needed when constant gain learning algorithms are used. If the mean dynamics map is stable but not contracting in every direction, and most eigenvalues of the map are close to the unit circle, the constant gain learning algorithm might diverge.

Keywords: Constant gain adaptive learning; E—stability; recursive least squares; stochastic gradient learning. (search for similar items in EconPapers)
JEL-codes: C62 C65 D83 E10 E17 (search for similar items in EconPapers)
Date: 2006-10
New Economics Papers: this item is included in nep-cba and nep-mac
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.cerge-ei.cz/pdf/wp/Wp309.pdf (application/pdf)

Related works:
Working Paper: Stochastic Gradient versus Recursive Least Squares Learning (2006)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cer:papers:wp309

Access Statistics for this paper

More papers in CERGE-EI Working Papers from The Center for Economic Research and Graduate Education - Economics Institute, Prague Contact information at EDIRC.
Bibliographic data for series maintained by Lucie Vasiljevova ().