| Abstract (2004) | |||||||||||||||
Abstract | |||||||||||||||
| We consider forward-looking models with agents following stochastic gradient (SG) adaptive learning. We examine how the conditions for stability of SG learning both differ from and are related to Estability, 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. However, generalized SG algorithms with constant gain have a deeper justification in terms of parameter drift, robustness and risk sensitivity. 1 | |||||||||||||||
Details der Publikation | |||||||||||||||
| |||||||||||||||