EconBase
← All papers

A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees

Victor Chernozhukov, Whitney K. Newey, Rahul Singh

arXiv 31 May 2021 · Statistics — Machine Learning · publishedBiometrika (2022) · 19 citations (OpenAlex)

arXiv:2105.15197 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Debiased machine learning is a meta algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i.e. scalar summaries, of machine learning algorithms. For example, an analyst may desire the confidence interval for a treatment effect estimated with a neural network. We provide a nonasymptotic debiased machine learning theorem that encompasses any global or local functional of any machine learning algorithm that satisfies a few simple, interpretable conditions. Formally, we prove consistency, Gaussian approximation, and semiparametric efficiency by finite sample arguments. The rate of convergence is $n^{-1/2}$ for global functionals, and it degrades gracefully for local functionals. Our results culminate in a simple set of conditions that an analyst can use to translate modern learning theory rates into traditional statistical inference. The conditions reveal a general double robustness property for ill posed inverse problems.

Citation extraction

46
references
73
in-text mentions
46
distinct cited
15
self-citations
5,872
main-text words

appendix boundary found by appendix_command · 33% 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
1Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo,… (2018) Double/debiased machine learning for treatment and structural parameters self0.9285380%
2Nathan Kallus, Xiaojie Mao, and Masatoshi Uehara (2021) Causal inference under unmeasured confounding with negative controls: A minimax learning approach0.7373367%
3Victor Chernozhukov, Juan Carlos Escanciano, Hidehiko Ichimura, Whit… (2016) Locally robust semiparametric estimation self0.73732100%
4Victor Chernozhukov, Whitney Newey, and Rahul Singh (2018) Debiased machine learning of global and local parameters using regularized Riesz representers self0.7218438%
5Victor Chernozhukov, Whitney K Newey, and Rahul Singh (2018) Automatic debiased machine learning of causal and structural effects self0.6444250%
6Rahul Singh, Maneesh Sahani, and Arthur Gretton (2019) Kernel instrumental variable regression self0.64422100%
7Rahul Singh (2021) Debiased kernel methods self0.64422100%
8Jason Abrevaya, Yu-Chin Hsu, and Robert P Lieli (2015) Estimating conditional average treatment effects0.5853333%
9Kyle Colangelo and Ying-Ying Lee (2020) Double debiased machine learning nonparametric inference with continuous treatments0.5112250%
10Hidehiko Ichimura and Whitney K Newey (2021) The influence function of semiparametric estimators self0.5112250%

Showing the top 10 of 46 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
1Generalized Kernel Ridge Regression for Causal Inference with Missing-at-Random Sample Selection0.87464
2Finite-Sample Guarantees for High-Dimensional DML0.87464
3Debiased Machine Learning without Sample-Splitting for Stable Estimators0.84333
4Kernel Ridge Riesz Representers: Generalization, Mis-specification, and the Counterfactual Effective Dimension0.72185
5Learning bounds for doubly-robust covariate shift adaptation0.64422
6Kernel Methods for Unobserved Confounding: Negative Controls, Proxies, and Instruments0.51132
7Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening0.51121
8Fisher-Schultz Lecture: Generic Machine Learning Inference on Heterogenous Treatment Effects in Randomized Experiments, with an Application to Immunization in India0.40511
9De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers0.40511
10Double Robustness for Complier Parameters and a Semiparametric Test for Complier Characteristics0.40511