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...

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...

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...

We examine a certain nonlinear model. Markov SSEs exist near an indeterminate steady state. ... We show that there exist Markov SSEs, that are E-stable, and therefore locally stable under adaptive learning, ...

We consider the stability under adaptive learning of the complete set of solutions x1 = ßE1*x1+1 when /ß/1. In addition to the fundamentals solution, the literature describes both finite-state Markov sunspot solutions, satisfying a resonant frequency condition, and autoregressive solutions...

We develop a monetary model with flexible supply of labor, cash in advance constraints and government spending financed by seignorage. This model has two regimes. One regime is conventional with two steady states. The other regime has a unique steady state which can be determinate or...