Generalisation and benign over-fitting for linear regression onto random functional covariates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jones, Andrew, Whiteley, Nick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911111175995392
author Jones, Andrew
Whiteley, Nick
author_facet Jones, Andrew
Whiteley, Nick
contents We study theoretical predictive performance of ridge and ridge-less least-squares regression when covariate vectors arise from evaluating $p$ random, means-square continuous functions over a latent metric space at $n$ random and unobserved locations, subject to additive noise. This leads us away from the standard assumption of i.i.d. data to a setting in which the $n$ covariate vectors are exchangeable but not independent in general. Under an assumption of independence across dimensions, $4$-th order moment, and other regularity conditions, we obtain probabilistic bounds on a notion of predictive excess risk adapted to our random functional covariate setting, making use of recent results of Barzilai and Shamir. We derive convergence rates in regimes where $p$ grows suitably fast relative to $n$, illustrating interplay between ingredients of the model in determining convergence behaviour and the role of additive covariate noise in benign-overfitting.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13895
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalisation and benign over-fitting for linear regression onto random functional covariates
Jones, Andrew
Whiteley, Nick
Machine Learning
We study theoretical predictive performance of ridge and ridge-less least-squares regression when covariate vectors arise from evaluating $p$ random, means-square continuous functions over a latent metric space at $n$ random and unobserved locations, subject to additive noise. This leads us away from the standard assumption of i.i.d. data to a setting in which the $n$ covariate vectors are exchangeable but not independent in general. Under an assumption of independence across dimensions, $4$-th order moment, and other regularity conditions, we obtain probabilistic bounds on a notion of predictive excess risk adapted to our random functional covariate setting, making use of recent results of Barzilai and Shamir. We derive convergence rates in regimes where $p$ grows suitably fast relative to $n$, illustrating interplay between ingredients of the model in determining convergence behaviour and the role of additive covariate noise in benign-overfitting.
title Generalisation and benign over-fitting for linear regression onto random functional covariates
topic Machine Learning
url https://arxiv.org/abs/2508.13895