We propose an efficient, reliable, and interpretable global solution method, the Deep learning-based algorithm for Heterogeneous Agent Models (DeepHAM), 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.

HKUST member only, no payment, auto confirm with 4 quota

This event is open to HKUST members only
 

How do I register?

• If you are a HKUST member, you can register using your ITSC network account.