Double ML

ML: Machine Learning

Double machine learning combines machine-learning estimates of nuisance relationships with residualization and orthogonal scores, often using cross-fitting to reduce overfitting bias. It is used for causal effects, dose-response curves, and risk estimation when data are confounded, selectively observed, or drawn from a shifted distribution. Current methods extend the framework with robust losses, covariate disentanglement, and specialized treatment representations, while theoretical work studies minimax limits in partial linear models. A central tension is that flexible nuisance models do not guarantee reliable estimates: learner choice, contamination, and confidence-interval coverage can all affect validity.

Latest papers

10 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Sharp Structure-Agnostic Minimax Risk for Partial Linear Models
Sep 7, 2026Haichen Hu, David Simchi-LeviDouble ML Semiparametric Inference
Center for Computational Science and Engineering, MIT · Department of Civil and Environmental Engineering, MIT · Institute for Data, Systems, and Society, MIT
Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalence
Jul 31, 2026Haozheng Xu, Siyuan Ma, Qingyan XiangDouble ML Causal Effect Estimation
Department of Biostatistics, Vanderbilt University Medical Center
A scalable online machine learning approach for Stock Recommendation
Jul 25, 2026Harsh NagarkarDouble ML Recommender Systems
California State University Chico · Chico, California, USA
From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
Jul 1, 2026Ka Ching Chan, Qiana Liu, Sanjib Tiwari +1Double ML Latent Variable Models
School of Business, Law, Humanities and Pathways, University of Southern Queensland, Springfield, 4300, Queensland, Australia
Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
Jun 12, 2026Annie Ulichney, Amanda CostonDouble ML Distribution Shift Robustness
Department of Statistics, University of California, Berkeley
Disentangled Double Machine Learning for Accurate Causal Effect Estimation
May 24, 2026Guodu Xiang, Kui Yu, Yujie Wang +3Double ML Causal Effect Estimation
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China · School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China
Predictive and Prescriptive AI toward Optimizing Wildfire Suppression
May 6, 2026Leonard Boussioux, Alexandre Jacquillat, Ryne Reger +1Double ML
Michael G. Foster School of Business and Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA · Operations Research Center and Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA
SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination
Apr 30, 2026Eichi UeharaDouble ML Robust Regression
Independent researcher.
Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach
Mar 2, 2026Yizhi Liu, Balaji Padmanabhan, Siva ViswanathanCausal Effect Estimation Causal Inference
Robert H. Smith School of Business, University of Maryland, College Park, MD, USA
The Impact of Formations on Football Matches Using Double Machine Learning. Is it worth parking the bus?
Feb 18, 2026Genís Ruiz-Menárguez, Llorenç BadiellaCausal Effect Estimation Double ML
Departament de Matemàtiques, Universitat Autònoma de Barcelona, Spain

Sep 7, 2026J/K move · Enter open · S save

Sharp Structure-Agnostic Minimax Risk for Partial Linear Models

Haichen Hu, David Simchi-Levi

Center for Computational Science and Engineering, MIT · Department of Civil and Environmental Engineering, MIT · Institute for Data, Systems, and Society, MIT

Double ML Semiparametric Inference Minimax Estimation Statistical Learning Theory

Open paper AskPDF arXiv

We characterize the sharp structure-agnostic minimax risk for coefficient estimation in the partial linear model when the outcome and treatment nuisances are learned by two distinct black-box learners, which resolves the open problem in double machine learning posed by Gu (2025). For each nuisance

q\in\{μ,π\}

, we characterize the available learner by an approximation-error budget

a_q

and a stochastic-error budget

s_q

, with the latter controlled through localized Rademacher complexity. Writing

\mathcal E_n

for the minimax mean-squared error, we show that

\mathcal E_n\asymp1\wedge\left\{\frac1n+\left(a_μa_π+\min\left\{a_πs_μ+s_π^2,\,a_μs_π+s_μ^2\right\}\right)^2\right\}.

The main new ingredient is a novel lower bound for the general two-learner problem. Our proof constructs four finite-mixture testing experiments using orthogonal code functions. Across these experiments, the hidden perturbations are placed outside both learner classes, outside only the treatment learner class, outside only the outcome learner class, or inside both learner classes. These four configurations capture, respectively, the interaction between the two approximation errors, the two asymmetric interactions between one learner's approximation error and the other learner's learning error, and the joint estimation difficulty of learning both nuisances. Combining the four resulting lower bounds yields the displayed rate, which matches the latest upper bound in Gu (2026). Our result shows that standard double machine learning can overstate the intrinsic difficulty of target estimation and provides a target-specific principle for learner selection: approximation error and stochastic complexity must be jointly balanced across the two nuisance learners rather than optimized separately.