DEEP EQUILIBRIUM NETS
International Economic Review · 2022-11 · 63 (4) · 1471-1525
DOI: 10.1111/iere.12575 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Economic Review, online erschienen am 16.05.2022. Verfasst von Marlon Azinovic und 2 weiteren Autor:innen. Die Arbeit wurde bisher 76-mal zitiert (Crossref) und nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
We introduce deep equilibrium nets (DEQNs)—a deep learning‐based method to compute approximate functional rational expectations equilibria of economic models featuring a significant amount of heterogeneity, uncertainty, and occasionally binding constraints. DEQNs are neural networks trained in an unsupervised fashion to satisfy all equilibrium conditions along simulated paths of the economy. Since DEQNs approximate the equilibrium functions directly, simulating the economy is computationally cheap, and training data can be generated at virtually zero cost. We demonstrate that DEQNs can accurately solve economically relevant models by applying them to two challenging life‐cycle models and a Bewley‐style model with aggregate risk.
Zitieren
APA
Azinovic, M., Gaegauf, L., & Scheidegger, S. (2022). DEEP EQUILIBRIUM NETS. International Economic Review, 63(4), 1471-1525. https://doi.org/10.1111/iere.12575
Vancouver
Azinovic M, Gaegauf L, Scheidegger S. DEEP EQUILIBRIUM NETS. International Economic Review. 2022;63(4):1471-1525. doi:10.1111/iere.12575
BibTeX
@article{Azinovic2022,
author = {Azinovic, Marlon and Gaegauf, Luca and Scheidegger, Simon},
title = {DEEP EQUILIBRIUM NETS},
journal = {International Economic Review},
year = {2022},
volume = {63},
number = {4},
pages = {1471--1525},
doi = {10.1111/iere.12575}
}
EUVIMED