Show simple item record

dc.contributor.authorEvans, George W., 1949-
dc.contributor.authorHonkapohja, Seppo, 1951-
dc.date.accessioned2005-12-15T16:42:42Z
dc.date.available2005-12-15T16:42:42Z
dc.date.issued2005-09-19
dc.identifier.urihttp://hdl.handle.net/1794/1927
dc.description35 p.en
dc.description.abstractWe study the properties of generalized stochastic gradient (GSG) learning in forwardlooking 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
dc.format.extent419658 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_USen
dc.publisherUniversity of Oregon, Dept of Economicsen
dc.relation.ispartofseriesUniversity of Oregon Economics Department Working Papers ; 2005-17en
dc.subjectAdaptive learningen
dc.subjectE-stabilityen
dc.subjectRecursive least squaresen
dc.subjectRobust estimationen
dc.titleGeneralized Stochastic Gradient Learningen
dc.typeWorking Paperen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record