Order-Explicit Linearization of High-Dimensional $U$-Statistics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ritzwoller, David M., Syrgkanis, Vasilis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910216796241920
author Ritzwoller, David M.
Syrgkanis, Vasilis
author_facet Ritzwoller, David M.
Syrgkanis, Vasilis
contents We give an order-explicit large deviation bound for the difference between a high-dimensional $U$-statistic and its Hájek projection. In particular, we show that any $U$-statistic of order $b$ on $n$ observations, with a $d$-dimensional kernel whose coordinates have $ψ_1$-Orlicz norm at most $ϕ$, has a maximum deviation from its Hájek projection of order $O_p(ϕb n^{-1}\log^2(dn))$. The proof relies on the development of novel order-explicit moment inequalities for higher-order Hoeffding components. We show that this rate is unimprovable, up to the polynomial factor on the logarithmic term. As corollaries, we obtain new Bernstein-type concentration and Gaussian approximation results for high-dimensional $U$-statistics. We apply these results to establish the consistency of a set of resampling-based simultaneous confidence intervals built around a class of nonparametric regression estimators constructed with subsampled kernels. This class encompasses several forms of random forest regression, including Generalized Random Forests.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07860
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Order-Explicit Linearization of High-Dimensional $U$-Statistics
Ritzwoller, David M.
Syrgkanis, Vasilis
Econometrics
Statistics Theory
Machine Learning
We give an order-explicit large deviation bound for the difference between a high-dimensional $U$-statistic and its Hájek projection. In particular, we show that any $U$-statistic of order $b$ on $n$ observations, with a $d$-dimensional kernel whose coordinates have $ψ_1$-Orlicz norm at most $ϕ$, has a maximum deviation from its Hájek projection of order $O_p(ϕb n^{-1}\log^2(dn))$. The proof relies on the development of novel order-explicit moment inequalities for higher-order Hoeffding components. We show that this rate is unimprovable, up to the polynomial factor on the logarithmic term. As corollaries, we obtain new Bernstein-type concentration and Gaussian approximation results for high-dimensional $U$-statistics. We apply these results to establish the consistency of a set of resampling-based simultaneous confidence intervals built around a class of nonparametric regression estimators constructed with subsampled kernels. This class encompasses several forms of random forest regression, including Generalized Random Forests.
title Order-Explicit Linearization of High-Dimensional $U$-Statistics
topic Econometrics
Statistics Theory
Machine Learning
url https://arxiv.org/abs/2405.07860