EconBase
← All papers

Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation

Jikai Jin, Vasilis Syrgkanis

arXiv 22 Feb 2024 · Statistics — Machine Learning · 1 citations (OpenAlex)

arXiv:2402.14264 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Average treatment effect estimation is the most central problem in causal inference with application to numerous disciplines. While many estimation strategies have been proposed in the literature, the statistical optimality of these methods has still remained an open area of investigation, especially in regimes where these methods do not achieve parametric rates. In this paper, we adopt the recently introduced structure-agnostic framework of statistical lower bounds, which poses no structural properties on the nuisance functions other than access to black-box estimators that achieve some statistical estimation rate. This framework is particularly appealing when one is only willing to consider estimation strategies that use non-parametric regression and classification oracles as black-box sub-processes. Within this framework, we prove the statistical optimality of the celebrated and widely used doubly robust estimators for both the Average Treatment Effect (ATE) and the Average Treatment Effect on the Treated (ATT), as well as weighted variants of the former, which arise in policy evaluation.

Citation extraction

79
references
127
in-text mentions
79
distinct cited
2
self-citations
8,136
main-text words

appendix boundary found by appendix_command · 47% 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
1Sivaraman Balakrishnan, Edward H Kennedy, and Larry Wasserman (2023) The fundamental limits of structure-agnostic functional estimation1.000124100%
2James Robins, Eric Tchetgen Tchetgen, Lingling Li, and Aad van der V… (2009) Semiparametric minimax rates1.000103100%
3S Balakrishnan and L Wasserman (2019) Hypothesis testing for densities and high-dimensional multinomials: Sharp local minimax rates0.81142100%
4Edward H Kennedy, Sivaraman Balakrishnan, James M Robins, and Larry… (2022) Minimax rates for heterogeneous causal effect estimation0.64441100%
5Ery Arias-Castro, Bruno Pelletier, and Venkatesh Saligrama (2018) Remember the curse of dimensionality: The case of goodness-of-fit testing in arbitrary dimension0.64422100%
6Max H Farrell, Tengyuan Liang, and Sanjog Misra (2021) Deep neural networks for estimation and inference0.64422100%
7Yu I Ingster (1994) Minimax detection of a signal in $_p$ metrics0.64422100%
8Anselm Johannes Schmidt-Hieber (2020) Nonparametric regression using deep neural networks with relu activation function0.64422100%
9Vasilis Syrgkanis and Manolis Zampetakis (2020) Estimation and inference with trees and forests in high dimensions self0.64422100%
10Alexandre B Tsybakov (2008) Introduction to nonparametric estimation0.64422100%

Showing the top 10 of 79 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
1On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models0.92844
2It's Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation0.87465
3Sharp Structure-Agnostic Lower Bounds for General Linear Functional Estimation0.73732
4Learning bounds for doubly-robust covariate shift adaptation0.64422
5On the Asymptotic Properties of Debiased Machine Learning Estimators0.58531
6What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness0.40511