Pith. sign in

REVIEW 1 cited by

Orthogonal Machine Learning: Power and Limitations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1711.00342 v6 pith:KGMGKJ7B submitted 2017-11-01 cs.LG econ.EMmath.STstat.MLstat.TH

classification cs.LGecon.EMmath.STstat.MLstat.TH
keywords parametersnuisanceinterestlearningmachineorthogonalrobustnesstreatment
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Double machine learning provides $\sqrt{n}$-consistent estimates of parameters of interest even when high-dimensional or nonparametric nuisance parameters are estimated at an $n^{-1/4}$ rate. The key is to employ Neyman-orthogonal moment equations which are first-order insensitive to perturbations in the nuisance parameters. We show that the $n^{-1/4}$ requirement can be improved to $n^{-1/(2k+2)}$ by employing a $k$-th order notion of orthogonality that grants robustness to more complex or higher-dimensional nuisance parameters. In the partially linear regression setting popular in causal inference, we show that we can construct second-order orthogonal moments if and only if the treatment residual is not normally distributed. Our proof relies on Stein's lemma and may be of independent interest. We conclude by demonstrating the robustness benefits of an explicit doubly-orthogonal estimation procedure for treatment effect.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Single Point Transductive Prediction

    stat.ML 2019-08 conditional novelty 7.0 of 10

    Two transductive estimators, a debiased-Lasso-style rule and an orthogonal-moment rule, achieve dimension-free O(1/n) prediction risk for a known test point, improving on ridge and Lasso.

Pith tools