← Back to all news
arXiv Statistics ML By Lin Liu, Rajarshi Mukherjee, James M Robins

On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models

Read the original on arXiv Statistics ML →

The paper investigates Double Machine Learning (DML) estimators under structure‑agnostic (SA) models, which assume the data‑generating law lies within a neighborhood of fixed machine‑learning estimates. It shows that for two of three studied functionals—the quadratic functional in the Gaussian sequence model and the quadratic density integral functional—the DML estimators are asymptotically inadmissible, being dominated by second‑order empirical higher‑order influence function (HOIF) estimators. For the third functional, the expected conditional covariance, both DML and HOIF estimators remain minimax but neither dominates the other.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv Machine Learning
Sep 10

Sharp Structure-Agnostic Minimax Risk for Partial Linear Models

arXiv:2609. 07997v1 Announce Type: new Abstract: 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).

By Haichen Hu, David Simchi-Levi
More like this →
arXiv Statistics ML
Aug 25

Model-Agnostic Covariate-Assisted Inference on Partially Identified Causal Effects

The paper introduces a model‑agnostic inference framework for partially identified causal effects that leverages covariate information without requiring discrete covariates or accurate conditional distribution estimates. Using duality theory for optimal transport, the method delivers uniformly valid inference in randomized experiments, is doubly robust in observational settings, achieves asymptotic unbiasedness when nuisance parameters converge semiparametrically, and allows multiplier‑bootstrap selection of covariates and models while remaining computationally efficient. Empirical applications show the approach consistently narrows identified sets and confidence intervals without imposing extra structural assumptions.

By Wenlong Ji, Lihua Lei, Asher Spector
More like this →