Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/19040 
Kompletter Metadatensatz
Erscheint in der Sammlung:
DublinCore-FeldWertSprache
dc.contributor.authorEvans, George W.en
dc.contributor.authorHonkapohja, Seppoen
dc.contributor.authorWilliams, Noahen
dc.date.accessioned2009-01-28T15:54:38Z-
dc.date.available2009-01-28T15:54:38Z-
dc.date.issued2005-
dc.identifier.urihttp://hdl.handle.net/10419/19040-
dc.description.abstractWe study the properties of generalized stochastic gradient (GSG) learning in forward-lookingmodels. 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 leastsquares learning. SG algorithms are sensitive to units of measurement and we show that thereis a transformation of variables for which E-stability governs SG stability. GSG algorithmswith constant gain have a deeper justification in terms of parameter drift, robustness and risksensitivity.en
dc.language.isoengen
dc.publisher|aCenter for Economic Studies and ifo Institute (CESifo) |cMunichen
dc.relation.ispartofseries|aCESifo Working Paper |x1576en
dc.subject.jelC65en
dc.subject.jelC62en
dc.subject.jelE17en
dc.subject.jelE10en
dc.subject.jelD83en
dc.subject.ddc330en
dc.subject.keywordadaptive learningen
dc.subject.keywordE-stabilityen
dc.subject.keywordrecursive least squaresen
dc.subject.keywordrobust estimationen
dc.subject.stwRationale Erwartungen
dc.subject.stwLernprozessen
dc.subject.stwPrognoseverfahrenen
dc.subject.stwGleichgewichtsstabilitäten
dc.subject.stwTheorieen
dc.titleGeneralized stochastic gradient learning-
dc.typeWorking Paperen
dc.identifier.ppn503712469en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen

Datei(en):
Datei
Größe
448.63 kB





Publikationen in EconStor sind urheberrechtlich geschützt.