|
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
|
| | |
| Title: | | Generalized stochastic gradient learning  |
| Authors: | | Evans, George W. Honkapohja, Seppo Williams, Noah |
| Issue Date: | | 2005 |
| Series/Report no.: | | CESifo working papers 1576 |
| 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. |
| Subjects: | | adaptive learning E-stability recursive least squares robust estimation |
| JEL: | | C65 C62 E17 E10 D83 |
| Document Type: | | Working Paper |
| Appears in Collections: | | CESifo Working Papers, CESifo Group Munich
|
| |
| | |
Download bibliographical data as:
BibTeX
|
| |
Share on:http://hdl.handle.net/10419/19040
|
Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.
|