Non-asymptotic confidence regions on RKHS. The Paley-Wiener and standard Sobolev space cases

2025/07/09 by Gamboa, Fabrice, Roustant, Olivier
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2507.06657

Abstract

We consider the problem of constructing a global, probabilistic, and non-asymptotic confidence region for an unknown function observed on a random design. The unknown function is assumed to lie in a reproducing kernel Hilbert space (RKHS). We show that this construction can be reduced to accurately estimating the RKHS norm of the unknown function. Our analysis primarily focuses both on the Paley-Wiener and on the standard Sobolev space settings.

Citations

• Scalable and adaptive prediction bands with kernel sum-of-squares

Related

• Non-parametric Stochastic Approximation with Large Step sizes
• Asymptotic Confidence Sets for General Nonparametric Regression and Classification by Regularized Kernel Methods
• Nonuniform sampling, reproducing kernels, and the associated Hilbert spaces
• Estimating linear response statistics using orthogonal polynomials: An RKHS formulation
• Uniform Function Estimators in Reproducing Kernel Hilbert Spaces