stat.MLNov 5, 2026

pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping

Authors: L. Bruni Bruno, P. Massa, E. Perracchione, M. Trombini

Organizations: Dipartimento di Scienze Matematiche Giuseppe Luigi Lagrange, Politecnico di Torino, Italy · Gruppo Nazionale per il Calcolo Scientifico INδAM, Rome, Italy · Institute for Data Science, University of Applied Sciences and Arts Northwestern Switzerland, Switzerland

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.

Figures & tables

Explore similar work

CardsList
  1. Practical Efficient Global Optimization is No-regret

    Mar 26, 2026Jingyi Wang, Haowei Wang, Nai-Yuan Chiang +3Bayesian OptimizationGlobal Optimization

  2. On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

    May 10, 2026Johannes Teutsch, Oleksii Molodchyk, Marion Leibold +2Kernel RegressionUncertainty Quantification