1. DSpace at MEDIU
  2. Harvested articles مقالات مستوردة من مؤسسات وجامعات عالمية
  3. EconStor
Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/10419/19040
Full metadata record
DC FieldValueLanguage
dc.creatorEvans, George W.-
dc.creatorHonkapohja, Seppo-
dc.creatorWilliams, Noah-
dc.date2005-
dc.date.accessioned2013-10-16T07:02:31Z-
dc.date.available2013-10-16T07:02:31Z-
dc.date.issued2013-10-16-
dc.identifierhttp://hdl.handle.net/10419/19040-
dc.identifierppn:503712469-
dc.identifier.urihttp://koha.mediu.edu.my:8181/xmlui/handle/10419/19040-
dc.descriptionWe 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.-
dc.languageeng-
dc.publisher-
dc.relationCESifo working papers 1576-
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-
dc.subjectC65-
dc.subjectC62-
dc.subjectE17-
dc.subjectE10-
dc.subjectD83-
dc.subjectddc:330-
dc.subjectadaptive learning-
dc.subjectE-stability-
dc.subjectrecursive least squares-
dc.subjectrobust estimation-
dc.subjectRationale Erwartung-
dc.subjectLernprozess-
dc.subjectPrognoseverfahren-
dc.subjectGleichgewichtsstabilität-
dc.subjectTheorie-
dc.titleGeneralized stochastic gradient learning-
dc.typedoc-type:workingPaper-
Appears in Collections:EconStor

Files in This Item:
There are no files associated with this item.
Show simple item record


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