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...

In a very broad class of dynamic linear models, if agents possess knowledge of current endogenous variables in a least-squares learning process, determinacy of a rational expectations (RE) equilibrium is sufficient but not necessary for learnability of that equilibrium. Thus, since learnability...

This paper presents a prototype model for development of the fiscal theory of the price level.' In this simple setting, the fiscal theory's distinctiveness relies upon adoption of a bubble solution, rather than the rational-expectations fundamentals solution. The paper then shows that the fiscal...

This paper explores the relationship between the closely linked concepts of E-stability and least-squares learnability, featured in recent work by Evans and Honkapohja (1999, 2001), and the minimum-state-variable (MSV) solution defined by McCallum (1983) and used by many researchers for rational...

It is argued that learnability/E-stability is a necessary condition for a RE solution to be plausible. A class of linear models considered by Evans and Honkapohja (2001) is shown to include all models of the form used by King and Watson (1998) and Klein (2000), which permits any number of lags,...

Bennett McCallum (2009), applying Evans and Honkapohja's (2001) results, argues that "learnability" can save New-Keynesian models from their indeterminacies. He claims the unique bounded equilibrium is learnable, and the explosive equilibria are not. However, he assumes that agents can directly...

In macroeconomic models with dispersed information, agents have an incentive to learn from endogenous variables, which themselves depend on the forecasts of others. This paper revisits the model of Townsend (1983) to characterize how this mechanism affects equilibrium dynamics. The first part of...

This paper investigates the role that imperfect knowledge about the structure of the economy plays in the formation of expectations, macroeconomic dynamics, and the efficient formulation of monetary policy. Economic agents rely on an adaptive learning technology to form expectations and to...

This paper explores two perspectives on the rational expectations hypothesis. One perspective is that of economic agents in such a model, who form inferences about the future using probabilities implied by the model. The other is that of an econometrician who makes inferences about the...

This paper investigates what features of an economy determine whether convergence under learning is fast or slow. In all of the models that we consider, people's beliefs about model outcomes are central determinants of those outcomes. We argue that under certain circumstances, convergence of a...