EconBase
← All papers

Deep Neural Networks for Estimation and Inference

Max H. Farrell, Tengyuan Liang, Sanjog Misra

arXiv 26 Sep 2018 · Econometrics · 44 citations (OpenAlex)

arXiv:1809.09953 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We study deep neural networks and their use in semiparametric inference. We establish novel rates of convergence for deep feedforward neural nets. Our new rates 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 estimation rates and semiparametric inference results handle the current standard architecture: fully connected feedforward neural networks (multi-layer perceptrons), with the now-common rectified linear unit activation function and a depth explicitly diverging with the sample size. We discuss other architectures as well, including fixed-width, very deep networks. We establish 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, such as treatment effects, expected welfare, and decomposition effects. Inference in many other semiparametric contexts can be readily obtained. We demonstrate the effectiveness of deep learning with a Monte Carlo analysis and an empirical application to direct mail marketing.

Citation extraction

96
references
158
in-text mentions
96
distinct cited
3
self-citations
16,362
main-text words

appendix boundary found by appendix_command · 72% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Hitsch, G. J. and S. Misra (2018) Heterogeneous Treatment Effects and Optimal Targeting Policy Evaluation1.00073100%
2Farrell, M. H (2015) Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations self1.00063100%
3Yarotsky, D (2017) Error bounds for approximations with deep ReLU networks0.8746467%
4Bartlett, P. L., N. Harvey, C. Liaw, and A. Mehrabian (2017) Nearly-tight VC-dimension bounds for piecewise linear neural networks, in0.8746367%
5Chen, X. and H. White (1999) Improved rates and asymptotic normality for nonparametric neural network estimators0.87452100%
6Yarotsky, D (2018) Optimal approximation of continuous functions by very deep ReLU networks0.8435460%
7Belloni, A., V. Chernozhukov, I. Fernández-Val, and C. Hansen (2017) Program Evaluation and Causal Inference With High-Dimensional Data0.84333100%
8Athey, S. and S. Wager (2018) Efficient Policy Learning0.81142100%
9Anthony, M. and P. L. Bartlett (1999) Neural Network Learning: Theoretical Foundations0.7373367%
10Belloni, A., V. Chernozhukov, and C. Hansen (2014) Inference on Treatment Effects after Selection Amongst High-Dimensional Controls0.73732100%

Showing the top 10 of 96 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1NEW APPROXIMATION RESULTS AND OPTIMAL ESTIMATION FOR FULLY CONNECTED DEEP NEURAL NETWORKS1.000364
2Deep Neural Network Estimation in Panel Data Models1.000154
3Dimension Reduction for Conditional Density Estimation with Applications to High-Dimensional Causal Inference1.00063
4Graph Neural Networks for Causal Inference Under Network Confounding1.00055
5Double Debiased Machine Learning Nonparametric Inference with Continuous Treatments0.971126
6Graph Neural Networks: Theory for Estimation with Application on Network Heterogeneity0.923147
7Structural Sieves0.85584
8High Dimensional Time Series Regression Models: Applications to Statistical Learning Methods0.81142
9Nonparametric rich covariateswithout saturation0.81142
10Econometrics with Pre-Trained Embeddings for Unstructured Data0.79464