Generalized Stochastic Gradient Learning
George W. Evans
University of Oregon - Department of Economics; University of St. Andrews - School of Economics and Finance
Bank of Finland; Centre for Economic Policy Research (CEPR); CESifo (Center for Economic Studies and Ifo Institute for Economic Research)
Princeton University - Department of Economics; National Bureau of Economic Research (NBER)
CESifo Working Paper No. 1576
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.
Number of Pages in PDF File: 40
Keywords: adaptive learning, E-stability, recursive least squares, robust estimation
JEL Classification: C62, C65, D83, E10, E17
Date posted: November 21, 2005
© 2016 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollobot1 in 0.719 seconds