The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Deep Neural Networks for Estimation and Inference
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665
Wage discrimination: Reduced form and structural estimates
Blinder, A. S. (1973) · The Journal of Human Resources · doi:10.2307/144855 · Cited by 6,922
Double/debiased machine learning for treatment and structural parameters
Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C., Newey, W., & Robins, J. (2018) · The Econometrics Journal · doi:10.1111/ectj.12097 · Cited by 2,946
Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
Wager, S., & Athey, S. (2018) · Journal of the American Statistical Association · doi:10.1080/01621459.2017.1319839 · Cited by 2,917
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838
Simultaneous analysis of Lasso and Dantzig selector
Bickel, P. J., Ritov, Y., & Tsybakov, A. B. (2009) · The Annals of Statistics · doi:10.1214/08-aos620 · Cited by 2,396
Inference on Treatment Effects after Selection among High-Dimensional Controls
Belloni, A., Chernozhukov, V., & Hansen, C. (2014) · The Review of Economic Studies · doi:10.1093/restud/rdt044 · Cited by 1,508
Optimal Global Rates of Convergence for Nonparametric Regression
Stone, C. J. (1982) · The Annals of Statistics · doi:10.1214/aos/1176345969 · Cited by 1,497
Error bounds for approximations with deep ReLU networks
Yarotsky, D. (2017) · Neural Networks · doi:10.1016/j.neunet.2017.07.002 · Cited by 1,085
Hahn, J. (1998) · Econometrica · doi:10.2307/2998560 · Cited by 996
On asymptotically optimal confidence regions and tests for high-dimensional models
van de Geer, S., Bühlmann, P., Ritov, Y., & Dezeure, R. (2014) · The Annals of Statistics · doi:10.1214/14-aos1221 · Cited by 822
Neural Network Learning: Theoretical Foundations
Anthony, M., & Bartlett, P. L. (1999) · Cambridge University Press eBooks · doi:10.1017/cbo9780511624216 · Cited by 598
Westreich, D., Lessler, J., & Funk, M. J. (2010) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2009.11.020 · Cited by 502
Mathematical Foundations of Infinite-Dimensional Statistical Models
Giné, E., & Nickl, R. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781107337862 · Cited by 402
Learning Representations for Counterfactual Inference
Johansson, F. D., Shalit, U., & Sontag, D. (2016) · arXiv · doi:10.48550/arxiv.1605.03661 · Cited by 396
Bartlett, P. L., Bousquet, O., & Mendelson, S. (2005) · The Annals of Statistics · doi:10.1214/009053605000000282 · Cited by 372
Local Rademacher complexities and oracle inequalities in risk minimization
Koltchinskii, V. I. (2006) · The Annals of Statistics · doi:10.1214/009053606000001019 · Cited by 364
Koltchinskii, V. (2011) · Lecture Notes in Mathematics · doi:10.1007/978-3-642-22147-7 · Cited by 346
Deep vs. shallow networks: An approximation theory perspective
Mhaskar, H. N., & Poggio, T. (2016) · Analysis and Applications · doi:10.1142/s0219530516400042 · Cited by 322
Robust inference on average treatment effects with possibly more covariates than observations
Farrell, M. H. (2015) · Journal of Econometrics · doi:10.1016/j.jeconom.2015.06.017 · Cited by 320
Self-citationProgram evaluation and causal inference with high-dimensional data
Belloni, A., Chernozhukov, V., Fern�ndez-Val, I., & Hansen, C. (2017) · Econometrica · doi:10.3982/ecta12723 · Cited by 317
Approximate Residual Balancing: Debiased Inference of Average Treatment Effects in High Dimensions
Athey, S., Imbens, G. W., & Wager, S. (2018) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/rssb.12268 · Cited by 311
Who Should Be Treated? Empirical Welfare Maximization Methods for Treatment Choice
Kitagawa, T., & Tetenov, A. (2018) · Econometrica · doi:10.3982/ecta13288 · Cited by 277
On deep learning as a remedy for the curse of dimensionality in nonparametric regression
Bauer, B., & Kohler, M. (2019) · The Annals of Statistics · doi:10.1214/18-aos1747 · Cited by 238
Rademacher Processes and Bounding the Risk of Function Learning
Koltchinskii, V., & Panchenko, D. (2000) · High Dimensional Probability II · doi:10.1007/978-1-4612-1358-1_29 · Cited by 209
Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations
Hanin, B. (2019) · Mathematics · doi:10.3390/math7100992 · Cited by 202
Semiparametric efficiency in GMM models with auxiliary data
Chen, X., Hong, H., & Tarozzi, A. (2008) · The Annals of Statistics · doi:10.1214/009053607000000947 · Cited by 199
Improved rates and asymptotic normality for nonparametric neural network estimators
Chen, X., & White, H. (1999) · IEEE Transactions on Information Theory · doi:10.1109/18.749011 · Cited by 182
A general double robustness result for estimating average treatment effects
Słoczyński, T., & Wooldridge, J. M. (2018) · Econometric Theory · doi:10.1017/s0266466617000056 · Cited by 122
Heterogeneous Treatment Effects and Optimal Targeting Policy Evaluation
Hitsch, G. J., Misra, S., & Zhang, W. W. (2018) · Quantitative Marketing and Economics · doi:10.1007/s11129-023-09278-5 · Cited by 110
Self-citationTan, Z. (2020) · The Annals of Statistics · doi:10.1214/19-aos1824 · Cited by 87
Two-Step Estimation and Inference with Possibly Many Included Covariates
Cattaneo, M. D., Michael Jansson, C., & Ma, X. (2018) · The Review of Economic Studies · doi:10.1093/restud/rdy053 · Cited by 62
Using Wasserstein Generative Adversarial Networks for the Design of Monte Carlo Simulations
Athey, S. C., Imbens, G. W., Metzger, J., & Munro, E. (2019) · National Bureau of Economic Research · doi:10.3386/w26566 · Cited by 25
Robust Inference Using Inverse Probability WeightingPreprint
Ma, X., & Wang, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11397 · Cited by 7
Cited by
Policy Learning With Observational Data
Athey, S., & Wager, S. (2021) · Econometrica · doi:10.3982/ecta15732 · Cited by 372
Ash, E., & Hansen, S. (2023) · Annual Review of Economics · doi:10.1146/annurev-economics-082222-074352 · Cited by 197
Debiased machine learning of conditional average treatment effects and other causal functions
Semenova, V., & Chernozhukov, V. (2021) · The Econometrics Journal · doi:10.1093/ectj/utaa027 · Cited by 167
Covariate-adjusted Fisher randomization tests for the average treatment effect
Zhao, A., & Ding, P. (2021) · Journal of Econometrics · doi:10.1016/j.jeconom.2021.04.007 · Cited by 40
AI for Customer Journeys: A Transformer Approach
Lu, Z., & Kannan, P. K. (2026) · Journal of Marketing Research · doi:10.1177/00222437251347268 · Cited by 21
Metadata
- Authors
- Farrell, M. H., Liang, T., & Misra, S.
- Venue
- Econometrica
- Publisher
- The Econometric Society
- Published
- 2021
- Volume
- 89
- Issue
- 1
- Pages
- 181-213
- ISSN
- 0012-9682 (ISSN-L)
- OpenAlex
- W2973682480
- Cited by
- 327
- References
- 37
- FWCI
- 29.63
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.