UD-DML: Uniform Design Subsampling for Double Machine Learning over Massive Data
arXiv:2605.05772
Abstract
Double machine learning (DML) delivers valid inference on low-dimensional causal parameters while permitting flexible nuisance estimation, but its computational cost becomes prohibitive once cross-fitted learners must be trained on massive observational data. Applying DML to a uniformly drawn subsample alleviates this burden, yet such a reduction disregards the geometry of the covariate space and can exacerbate treated-control imbalance as well as overlap deficiency. We propose Uniform Design Double Machine Learning (UD-DML), a design-based subsampling strategy for average treatment effect (ATE) estimation. UD-DML first constructs a low-discrepancy skeleton in a PCA-rotated covariate space under the mixture-discrepancy criterion, and then assigns, to each skeleton point, the nearest treated and control units via KD-tree search. The resulting matched subsample is, by construction, both representative of the full covariate distribution and balanced across treatment arms; cross-fitted DML is subsequently applied to it. We establish discrepancy-based guarantees for representativeness and balance, and prove that the UD-DML estimator is -asymptotically normal under mild conditions, where the selected subsample size . The dominant nuisance-fitting cost is thereby reduced from the -scale to the -scale. Monte Carlo experiments show that UD-DML attains lower RMSE, narrower confidence intervals and more reliable coverage than uniform subsampling, with the largest gains in low-overlap and misspecified regimes. An application to a large observational dataset further demonstrates its practical feasibility.