Exploiting Symmetry in High-Dimensional Dynamic Programming

Fernández-Villaverde, Jesús, Mahdi Ebrahimi Kahou, Jesse Perla () and Arnav Sood
Authors registered in the RePEc Author Service: Jesus Fernandez-Villaverde

No 16285, CEPR Discussion Papers from Centre for Economic Policy Research

Abstract: We propose a new method for solving high-dimensional dynamic programming problems and recursive competitive equilibria with a large (but finite) number of heterogeneous agents using deep learning. The ``curse of dimensionality'' is avoided due to four complementary techniques: (1) exploiting symmetry in the approximate law of motion and the value function; (2) constructing a concentration of measure to calculate high-dimensional expectations using a single Monte Carlo draw from the distribution of idiosyncratic shocks; (3) sampling methods to ensure the model fits along manifolds of interest; and (4) selecting the most generalizable over-parameterized deep learning approximation without calculating the stationary distribution or applying a transversality condition. As an application, we solve a global solution of a multi-firm version of the classic Lucas and Prescott (1971) model of ``investment under uncertainty.'' First, we compare the solution against a linear-quadratic Gaussian version for validation and benchmarking. Next, we solve nonlinear versions with aggregate shocks. Finally, we describe how our approach applies to a large class of models in economics.

Keywords: Machine learning; Dynamic programming (search for similar items in EconPapers)
Date: 2021-06
References: Add references at CitEc
Citations:

Downloads: (external link)
https://cepr.org/publications/DP16285 (application/pdf)

Related works:
Working Paper: Exploiting Symmetry in High-Dimensional Dynamic Programming (2021)
Working Paper: Exploiting Symmetry in High-Dimensional Dynamic Programming (2021)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cpr:ceprdp:16285

Ordering information: This working paper can be ordered from
https://cepr.org/publications/DP16285

Access Statistics for this paper

More papers in CEPR Discussion Papers from Centre for Economic Policy Research 33 Great Sutton Street, London EC1V 0DX, UK.
Bibliographic data for series maintained by CEPR ().