mlsanityData to 7 Oct 2026

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

arXiv 2402.14264 ↗First posted 22 Feb 2024stat.ML cs.LG econ.EMcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 17 of its 83 references that are in the map. First posted on arXiv 22 Feb 2024.

Builds on

17 of 83 references.

References · 17

  1. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 597
  2. 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
  3. 2016Generalized Random Forestscited by 309
  4. 2019Orthogonal Statistical Learningcited by 150
  5. 2019FLAML: A Fast and Lightweight AutoML Librarycited by 104
  6. 2017Double/Debiased/Neyman Machine Learning of Treatment Effectscited by 76
  7. 2020AutoML to Date and Beyond: Challenges and Opportunitiescited by 63
  8. 2013Robust Inference on Average Treatment Effects with Possibly More Covariates than Observationscited by 38
  9. 2020Estimation and Inference with Trees and Forests in High Dimensionscited by 14
  10. 2022Debiased Machine Learning without Sample-Splitting for Stable Estimatorscited by 13
  11. 2023The Fundamental Limits of Structure-Agnostic Functional Estimationcited by 12
  12. 2013Uniform Post Selection Inference for LAD Regression and Other Z-estimation problemscited by 11
5 more
  1. 2017Hypothesis Testing For Densities and High-Dimensional Multinomials: Sharp Local Minimax Ratescited by 11
  2. 2024Hyperparameter Tuning for Causal Inference with Double Machine Learning: A Simulation Studycited by 11
  3. 2015Higher Order Tangent Spaces and Influence Functionscited by 9
  4. 2021A Simple and General Debiased Machine Learning Theorem with Finite Sample Guaranteescited by 9
  5. 2019Minimax Semiparametric Learning With Approximate Sparsitycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2025Orthogonal Representation Learning for Estimating Causal Quantitiescited by 4
  2. 2026Optimally taming biases in black-box models for efficient semiparametric estimationcited by 3
  3. 2026On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Modelscited by 2
  4. 2024Causal Inference for Genomic Data with Multiple Heterogeneous Outcomescited by 1
  5. 2025GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomescited by 1