EUVIMEDEUVIMED entdecken
Crossref

Orthogonal statistical learning

Dylan J. Foster, Vasilis Syrgkanis

The Annals of Statistics · 01.06.2023 · 51 (3) · 879-908

DOI: 10.1214/23-aos2258 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Annals of Statistics, erschienen am 01.06.2023. Verfasst von Dylan J. Foster und 1 weiteren Autor:innen. Die Arbeit wurde bisher 67-mal zitiert (Crossref) und nennt 92 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We provide nonasymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input arbitrary estimation algorithms for the target parameter and nuisance parameter. We show that if the population risk satisfies a condition called Neyman orthogonality, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second order. Our theorem is agnostic to the particular algorithms used for the target and nuisance and only makes an assumption on their individual performance. This enables the use of a plethora of existing results from machine learning to give new guarantees for learning with a nuisance component. Moreover, by focusing on excess risk rather than parameter estimation, we can provide rates under weaker assumptions than in previous works and accommodate settings in which the target parameter belongs to a complex nonparametric class. We provide conditions on the metric entropy of the nuisance and target classes such that oracle rates of the same order, as if we knew the nuisance parameter, are achieved.

Zitieren

APA

Foster, D. J., & Syrgkanis, V. (2023). Orthogonal statistical learning. The Annals of Statistics, 51(3), 879-908. https://doi.org/10.1214/23-aos2258

Vancouver

Foster DJ, Syrgkanis V. Orthogonal statistical learning. The Annals of Statistics. 2023;51(3):879-908. doi:10.1214/23-aos2258

BibTeX
@article{Foster2023,
  author = {Foster, Dylan J. and Syrgkanis, Vasilis},
  title = {Orthogonal statistical learning},
  journal = {The Annals of Statistics},
  year = {2023},
  volume = {51},
  number = {3},
  pages = {879--908},
  doi = {10.1214/23-aos2258}
}
Kostenlos starten →