pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping
Abstract
Kernel-based greedy algorithms select suitable approximation nodes by minimizing point-wise error indicators, such as the power function; in this context, they are usually referred to as p-greedy approaches. In the presence of noisy data, deterministic criteria may fail, as the discrepancy between the true solution and its estimate is influenced by both approximation error and noise amplification, and the balance between the two is unknown. This study explicitly separates these two contributions, which are governed by the power function and a Lebesgue-type term, respectively. These bounds motivate the use of the Stein's unbiased risk estimator (SURE) as a proxy of the mean squared error, which in turn provides a principled and computable stopping criterion for the number of nodes to select in the p-greedy procedure. Numerical experiments demonstrate that this approach effectively balances deterministic accuracy and statistical noise contributions.
Versions
Related
- Greedy multiscale kernel algorithms
- A Robust Fast Greedy Model Averaging Method for High-Dimensional Regression with Outliers
- When is early stopping beneficial under label noise? A phase diagram for kernel gradient flow
- Kernel Density Regression Estimation with Covariates on Riemannian Manifolds
- Robust Error Bounds for Vector-Valued Kernel Ridge Regression
BibTeX
@misc{bruno2026pesto,
title = {{pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping}},
author = {L. Bruni Bruno and P. Massa and E. Perracchione and M. Trombini},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08555},
eprint = {2611.08555},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08555},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping
AU - L. Bruni Bruno
AU - P. Massa
AU - E. Perracchione
AU - M. Trombini
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.08555
UR - https://arxiv.org/abs/2611.08555
AB - Kernel-based greedy algorithms select suitable approximation nodes by minimizing point-wise error indicators, such as the power function; in this context, they are usually referred to as p-greedy approaches. In the presence of noisy data, deterministic criteria may fail, as the discrepancy between the true solution and its estimate is influenced by both approximation error and noise amplification, and the balance between the two is unknown. This study explicitly separates these two contributions, which are governed by the power function and a Lebesgue-type term, respectively. These bounds motivate the use of the Stein's unbiased risk estimator (SURE) as a proxy of the mean squared error, which in turn provides a principled and computable stopping criterion for the number of nodes to select in the p-greedy procedure. Numerical experiments demonstrate that this approach effectively balances deterministic accuracy and statistical noise contributions.
ER -