Similar Search Results

Generalized stochastic gradient learning

Evans, George W.; Honkapohja, Seppo; Williams, Noah - 2005

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...

Persistent link: https://www.econbiz.de/10010261355

Generalized Stochastic Gradient Learning

Evans, George W.; Honkapohja, Seppo; Williams, Noah - CESifo - 2005

Persistent link: https://www.econbiz.de/10005406017

Escape Dynamics: A Continuous—Time Approximation

Kolyuzhnov, Dmitri; Bogomolova, Anna; Slobodyan, Sergey - Center for Economic Research and Graduate Education and … - 2006

constant gain. This approach is based on applying results of continuous—time version of large deviations theory to the … by CWS. We express reservations regarding applicability of escape dynamics theory to characterization of mean escape time … considerations and formulae generate much better mean escape time results than the large deviations theory. We explain it by …

Persistent link: https://www.econbiz.de/10005086597

Stochastic Gradient versus Recursive Least Squares Learning

Slobodyan, Sergey; Bogomolova, Anna; Kolyuzhnov, Dmitri - Center for Economic Research and Graduate Education and … - 2006

In this paper, we perform an in—depth investigation of relative merits of two adaptive learning algorithms with constant gain, Recursive Least Squares (RLS) and Stochastic Gradient (SG), using the Phelps model of monetary policy as a testing ground. The behavior of the two learning algorithms...

Persistent link: https://www.econbiz.de/10005086661

Generalized Stochastic Gradient Learning

Evans, G.W.; Honkapohja, S.; Williams, N. - Faculty of Economics, University of Cambridge - 2005

We 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 di1er from and are related to E-stability, which governs stability under least squares learning. SG...

Persistent link: https://www.econbiz.de/10005647409

Generalized Stochastic Gradient Learning

Evans, George W.; Honkapohja, Seppo; Williams, Noah - Department of Economics, University of Oregon - 2005

We 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...

Persistent link: https://www.econbiz.de/10005593751

Stochastic Gradient versus Recursive Least Squares Learning

Slobodyan, Sergey; Bogomolova, Anna; Kolyuzhnov, Dmitri - Society for Computational Economics - SCE - 2006

In this paper we perform an inâ€”depth investigation of relative merits of two adaptive learning algorithms with constant gain, Recursive Least Squares (RLS) and Stochastic Gradient (SG), using the Phelps model of monetary policy as a testing ground. The behavior of the two learning...

Persistent link: https://www.econbiz.de/10005342959