Training Neural Networks Embedded in Dynamic Discrete Choice Models
TLDR
New UFXP/OUFXP estimators enable training neural networks in dynamic discrete choice models by avoiding large linear systems, improving flexibility.
Key contributions
- Introduces UFXP and OUFXP, the first general estimators for infinite-horizon dynamic discrete choice models.
- Eliminates large systems of linear equations in estimation, simplifying computation significantly.
- Utilizes a dual representation of Bellman's equation to separate utility parameters from the fixed point.
- Enables non-parametric utility function approximation using flexible neural networks.
Why it matters
This paper offers a significant advancement in estimating complex economic models. By enabling neural networks and simplifying computation, it allows for more flexible and realistic modeling of decision-making. This opens new avenues for research in economics and related fields.
Original Abstract
We develop the first general-purpose estimator for infinite-horizon dynamic discrete choice models whose estimation problem, after pre-computation, is unencumbered by large systems of linear equations -- either imposed as constraints, or embedded in the objective function. Our unnested fixed point (UFXP) and optimal unnested fixed point (OUFXP) estimators exploit a dual representation of Bellman's equation to separate the utility parameters from the dynamic programming fixed point. We establish the consistency and asymptotic normality of UFXP and OUFXP, as well as the efficiency of the latter. Our estimators enable researchers to model utility functions non-parametrically via flexible neural-network approximations.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.