EconStor >
ifo Institut – Leibniz-Institut für Wirtschaftsforschung an der Universität München >
CESifo Working Papers, CESifo Group Munich >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/19040
  

Full metadata record

DC FieldValueLanguage
dc.contributor.authorEvans, George W.en_US
dc.contributor.authorHonkapohja, Seppoen_US
dc.contributor.authorWilliams, Noahen_US
dc.date.accessioned2009-01-28T15:54:38Z-
dc.date.available2009-01-28T15:54:38Z-
dc.date.issued2005en_US
dc.identifier.urihttp://hdl.handle.net/10419/19040-
dc.description.abstractWe 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.en_US
dc.language.isoengen_US
dc.publisheren_US
dc.relation.ispartofseriesCESifo working papers 1576en_US
dc.subject.jelC65en_US
dc.subject.jelC62en_US
dc.subject.jelE17en_US
dc.subject.jelE10en_US
dc.subject.jelD83en_US
dc.subject.ddc330en_US
dc.subject.keywordadaptive learningen_US
dc.subject.keywordE-stabilityen_US
dc.subject.keywordrecursive least squaresen_US
dc.subject.keywordrobust estimationen_US
dc.subject.stwRationale Erwartungen_US
dc.subject.stwLernprozessen_US
dc.subject.stwPrognoseverfahrenen_US
dc.subject.stwGleichgewichtsstabilitäten_US
dc.subject.stwTheorieen_US
dc.titleGeneralized stochastic gradient learningen_US
dc.typeWorking Paperen_US
dc.identifier.ppn503712469en_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-
Appears in Collections:CESifo Working Papers, CESifo Group Munich

Files in This Item:
File Description SizeFormat
cesifo1_wp1576.pdf448.63 kBAdobe PDF
No. of Downloads: Counter Stats
Show simple item record
Download bibliographical data as: BibTeX

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.