under private agent learning can in some cases be stable when the observed sunspot has a suitable time series structure. In …

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 …

adaptive learning. We reconsider this issue and analyze the full set of solutions for the linearized model. Our main focus is … learning if agents can utilize contemporaneous data. However, in an economy populated by a mixture of agents, some of whom only …

adaptive learning. We reconsider this issue and analyze the full set of solutions for the linearized model. Our main focus is … learning if agents can utilize contemporaneous data. However, in an economy populated by a mixture of agents, some of whom only …

(X), provided F´(X)> 1. 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 to the model when . In addition to … representation used by agents in the learning process. Only the finite-state Markov sunspot solutions can be stable under learning. …

high steady states are expectationally stable (E-stable), and thus locally stable under learning, while the middle steady …

stable under adaptive learning, taking the form of noisy finite state Markov processes at resonant frequencies. For a range …

under private agent learning can in some cases be stable when the observed sunspot has a suitable time series structure. In …