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

arXiv: https://arxiv.org/abs/2402.14264 · HTML: https://mlsanity.com/paper/2402.14264/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 83 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Nonparametric regression using deep neural networks with ReLU activation function](https://mlsanity.com/paper/1708.06633/) (2017)
- [Generalized Random Forests](https://mlsanity.com/paper/1610.01271/) (2016)
- [Orthogonal Statistical Learning](https://mlsanity.com/paper/1901.09036/) (2019)
- [FLAML: A Fast and Lightweight AutoML Library](https://mlsanity.com/paper/1911.04706/) (2019)
- [Double/Debiased/Neyman Machine Learning of Treatment Effects](https://mlsanity.com/paper/1701.08687/) (2017)
- [AutoML to Date and Beyond: Challenges and Opportunities](https://mlsanity.com/paper/2010.10777/) (2020)
- [Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations](https://mlsanity.com/paper/1309.4686/) (2013)
- [Estimation and Inference with Trees and Forests in High Dimensions](https://mlsanity.com/paper/2007.03210/) (2020)
- [Debiased Machine Learning without Sample-Splitting for Stable Estimators](https://mlsanity.com/paper/2206.01825/) (2022)
- [The Fundamental Limits of Structure-Agnostic Functional Estimation](https://mlsanity.com/paper/2305.04116/) (2023)
- [Uniform Post Selection Inference for LAD Regression and Other Z-estimation problems](https://mlsanity.com/paper/1304.0282/) (2013)
- [Hypothesis Testing For Densities and High-Dimensional Multinomials: Sharp Local Minimax Rates](https://mlsanity.com/paper/1706.10003/) (2017)
- [Hyperparameter Tuning for Causal Inference with Double Machine Learning: A Simulation Study](https://mlsanity.com/paper/2402.04674/) (2024)
- [Higher Order Tangent Spaces and Influence Functions](https://mlsanity.com/paper/1502.00812/) (2015)
- [A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees](https://mlsanity.com/paper/2105.15197/) (2021)
- [Minimax Semiparametric Learning With Approximate Sparsity](https://mlsanity.com/paper/1912.12213/) (2019)

## Built on by (most cited first, 6 of 6)

- [Orthogonal Representation Learning for Estimating Causal Quantities](https://mlsanity.com/paper/2502.04274/) (2025)
- [Optimally taming biases in black-box models for efficient semiparametric estimation](https://mlsanity.com/paper/2606.06368/) (2026)
- [On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models](https://mlsanity.com/paper/2606.22391/) (2026)
- [Causal Inference for Genomic Data with Multiple Heterogeneous Outcomes](https://mlsanity.com/paper/2404.09119/) (2024)
- [GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes](https://mlsanity.com/paper/2509.22953/) (2025)
- [Optimal Inference with Black-box Predictions](https://mlsanity.com/paper/2608.10155/) (2026)

## 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.