DeepHAM: A Global Solution Method for Heterogeneous Agent Models with Aggregate Shocks
This method addresses the need for efficient and interpretable solutions in macroeconomics, enabling better study of heterogeneity and policy impacts, though it appears incremental as an extension of existing deep learning techniques to this domain.
The authors tackled the challenge of solving high-dimensional heterogeneous agent models with aggregate shocks by proposing DeepHAM, a deep learning-based global solution method that approximates state distributions with generalized moments and uses neural networks for value and policy functions, achieving computational efficiency without the curse of dimensionality.
An efficient, reliable, and interpretable global solution method, the Deep learning-based algorithm for Heterogeneous Agent Models (DeepHAM), is proposed for solving high dimensional heterogeneous agent models with aggregate shocks. The state distribution is approximately represented by a set of optimal generalized moments. Deep neural networks are used to approximate the value and policy functions, and the objective is optimized over directly simulated paths. In addition to being an accurate global solver, this method has three additional features. First, it is computationally efficient in solving complex heterogeneous agent models, and it does not suffer from the curse of dimensionality. Second, it provides a general and interpretable representation of the distribution over individual states, which is crucial in addressing the classical question of whether and how heterogeneity matters in macroeconomics. Third, it solves the constrained efficiency problem as easily as it solves the competitive equilibrium, which opens up new possibilities for studying optimal monetary and fiscal policies in heterogeneous agent models with aggregate shocks.