Generalized Stochastic Gradient Learning

George William Evans (), Seppo Mikko Sakari Honkapohja () and Noah Williams ()

No CESifo Working Paper No. 1576, CESifo Working Paper Series from CESifo Group Munich

Abstract: 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.

Keywords: adaptive learning; E-stability; recursive least squares; robust estimation (search for similar items in EconPapers)
JEL-codes: C62 C65 D83 E10 E17 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-mac
Date: 2005
View list of references View citations in EconPapers

Downloads: (external link)
http://www.cesifo-group.de/DocCIDL/cesifo1_wp1576.pdf (application/pdf)

Related works:
Working Paper: Generalized Stochastic Gradient Learning (2005)
Working Paper: Generalized Stochastic Gradient Learning (2005)
Working Paper: Generalized Stochastic Gradient Learning (2008)
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: http://EconPapers.repec.org/RePEc:ces:ceswps:_1576

Access Statistics for this paper

More papers in CESifo Working Paper Series from CESifo Group Munich
Address: Poschingerstrasse 5, 81679 Munich
Series data maintained by Julio Saavedra ().