It’s Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation

Jikai Jin, Lester Mackey, Vasilis Syrgkanis

Keywords: structure-agnostic causal inference, minimax, causal machine learning, semiparametric inference, Neyman orthogonality, double machine learning, higher-order robustness

TL;DR: We show that the statistical optimality of estimation methods for causal inference depend in a surprising way on the distribution of the treatment noise.

Abstract: Structure-agnostic causal inference studies the statistical limits of treatment effect estimation, when given access to black-box ML models that estimate nuisance components of the data generating process, such as estimates of the outcome regression and the treatment propensity. Here, we find that the answer depends in a surprising way on the distribution of the treatment noise. Focusing on the partially linear outcome model of \citet{robinson1988root}, we first show that the widely adopted double machine learning (DML) estimator is minimax rate-optimal for Gaussian treatment noise, resolving an open problem of \citet{mackey2018orthogonal}. Meanwhile, for independent non-Gaussian treatment noise, we show that DML is always suboptimal by constructing new practical procedures with higher-order robustness to nuisance errors. These *ACE* procedures use structure-agnostic cumulant estimators to achieve $r$-th order insensitivity to nuisance errors whenever the $(r+1)$-st treatment cumulant is non-zero. We complement these core results with novel minimax guarantees for binary treatments in the partially linear outcome model. Finally, using synthetic demand estimation experiments, we demonstrate the practical benefits of our higher-order robust estimators.

Primary Area: Theory (e.g., control theory, learning theory, algorithmic game theory)

Submission Number: 6902