Generalized Stochastic Gradient Learning
George Evans,
Seppo Honkapohja and
Noah Williams
No 317, NBER Technical Working Papers from National Bureau of Economic Research, Inc
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.
JEL-codes: C62 C65 D83 E10 E17 (search for similar items in EconPapers)
Date: 2005-10
New Economics Papers: this item is included in nep-cmp, nep-evo and nep-mac
Note: TWP
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (17)
Downloads: (external link)
http://www.nber.org/papers/t0317.pdf (application/pdf)
Related works:
Journal Article: GENERALIZED STOCHASTIC GRADIENT LEARNING (2010)
Working Paper: Generalized Stochastic Gradient Learning (2008) 
Working Paper: Generalized Stochastic Gradient Learning (2005) 
Working Paper: Generalized Stochastic Gradient Learning (2005) 
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:nbr:nberte:0317
Ordering information: This working paper can be ordered from
http://www.nber.org/papers/t0317
Access Statistics for this paper
More papers in NBER Technical Working Papers from National Bureau of Economic Research, Inc National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.. Contact information at EDIRC.
Bibliographic data for series maintained by ().