Optimal Sampling for Kernel Quadrature on Unbounded Domains

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bandoni, Edoardo, Robert, Christian, Stoehr, Julien
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911693956710400
author Bandoni, Edoardo
Robert, Christian
Stoehr, Julien
author_facet Bandoni, Edoardo
Robert, Christian
Stoehr, Julien
contents Kernel quadrature is widely used to approximate integrals of smooth functions, with worst-case error typically decaying at the minimax rate $n^{-α/d}$ for smoothness $α$ in dimension $d$. Existing rate-optimal methods often depend on deterministic point sets tailored to a specific kernel, making them sensitive to misspecification and less robust in practice. In this work, we study randomized quadrature methods with a focus on robustness rather than kernel-specific optimality. We construct an explicit, $n$-dependent sampling distribution that achieves minimax rates for worst-case error over smoothness classes without requiring knowledge of the kernel. This kernel-agnostic design improves robustness while retaining optimal rates. Our analysis includes unbounded sampling measures such as Gaussian and Student-$t$ distributions, extending beyond compact domains. The results provide both theoretical guarantees and a practical recipe for robust, rate-optimal randomized quadrature.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18134
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Optimal Sampling for Kernel Quadrature on Unbounded Domains
Bandoni, Edoardo
Robert, Christian
Stoehr, Julien
Computation
Methodology
Kernel quadrature is widely used to approximate integrals of smooth functions, with worst-case error typically decaying at the minimax rate $n^{-α/d}$ for smoothness $α$ in dimension $d$. Existing rate-optimal methods often depend on deterministic point sets tailored to a specific kernel, making them sensitive to misspecification and less robust in practice. In this work, we study randomized quadrature methods with a focus on robustness rather than kernel-specific optimality. We construct an explicit, $n$-dependent sampling distribution that achieves minimax rates for worst-case error over smoothness classes without requiring knowledge of the kernel. This kernel-agnostic design improves robustness while retaining optimal rates. Our analysis includes unbounded sampling measures such as Gaussian and Student-$t$ distributions, extending beyond compact domains. The results provide both theoretical guarantees and a practical recipe for robust, rate-optimal randomized quadrature.
title Optimal Sampling for Kernel Quadrature on Unbounded Domains
topic Computation
Methodology
url https://arxiv.org/abs/2605.18134