Journal
ECONOMETRICA
Volume 89, Issue 1, Pages 181-213Publisher
WILEY
DOI: 10.3982/ECTA16901
Keywords
Deep learning; neural networks; rectified linear unit; nonasymptotic bounds; convergence rates; semiparametric inference; treatment effects; program evaluation
Categories
Funding
- George C. Tiao Fellowship
- Neubauer Family Foundation
Ask authors/readers for more resources
This study focuses on deep neural networks in semiparametric inference, establishing novel nonasymptotic high probability bounds and demonstrating fast rates of convergence for valid second-step inference after deep learning. Various neural network architectures are explored, with applications to a general class of nonparametric regression-type loss functions. The effectiveness of deep learning is showcased through an empirical application to direct mail marketing.
We study deep neural networks and their use in semiparametric inference. We establish novel nonasymptotic high probability bounds for deep feedforward neural nets. These deliver rates of convergence that are sufficiently fast (in some cases minimax optimal) to allow us to establish valid second-step inference after first-step estimation with deep learning, a result also new to the literature. Our nonasymptotic high probability bounds, and the subsequent semiparametric inference, treat the current standard architecture: fully connected feedforward neural networks (multilayer perceptrons), with the now-common rectified linear unit activation function, unbounded weights, and a depth explicitly diverging with the sample size. We discuss other architectures as well, including fixed-width, very deep networks. We establish the nonasymptotic bounds for these deep nets for a general class of nonparametric regression-type loss functions, which includes as special cases least squares, logistic regression, and other generalized linear models. We then apply our theory to develop semiparametric inference, focusing on causal parameters for concreteness, and demonstrate the effectiveness of deep learning with an empirical application to direct mail marketing.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available