Asymptotic Optimism of Random-Design Linear and Kernel Regression Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Luo, Hengrui, Zhu, Yunzhang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908491246993408
author Luo, Hengrui
Zhu, Yunzhang
author_facet Luo, Hengrui
Zhu, Yunzhang
contents We derived the closed-form asymptotic optimism of linear regression models under random designs, and generalizes it to kernel ridge regression. Using scaled asymptotic optimism as a generic predictive model complexity measure, we studied the fundamental different behaviors of linear regression model, tangent kernel (NTK) regression model and three-layer fully connected neural networks (NN). Our contribution is two-fold: we provided theoretical ground for using scaled optimism as a model predictive complexity measure; and we show empirically that NN with ReLUs behaves differently from kernel models under this measure. With resampling techniques, we can also compute the optimism for regression models with real data.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12999
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asymptotic Optimism of Random-Design Linear and Kernel Regression Models
Luo, Hengrui
Zhu, Yunzhang
Machine Learning
Statistics Theory
68T05, 68Q32
We derived the closed-form asymptotic optimism of linear regression models under random designs, and generalizes it to kernel ridge regression. Using scaled asymptotic optimism as a generic predictive model complexity measure, we studied the fundamental different behaviors of linear regression model, tangent kernel (NTK) regression model and three-layer fully connected neural networks (NN). Our contribution is two-fold: we provided theoretical ground for using scaled optimism as a model predictive complexity measure; and we show empirically that NN with ReLUs behaves differently from kernel models under this measure. With resampling techniques, we can also compute the optimism for regression models with real data.
title Asymptotic Optimism of Random-Design Linear and Kernel Regression Models
topic Machine Learning
Statistics Theory
68T05, 68Q32
url https://arxiv.org/abs/2502.12999