Nonparametric, Nonasymptotic Confidence Bands with Paley-Wiener Kernels for Band-Limited Functions
Csáji, Balázs Csanád, Horváth, Bálint
–arXiv.org Artificial Intelligence
The paper introduces a method to construct confidence bands for bounded, band-limited functions based on a finite sample of input-output pairs. The approach is distribution-free w.r.t. the observation noises and only the knowledge of the input distribution is assumed. It is nonparametric, that is, it does not require a parametric model of the regression function and the regions have non-asymptotic guarantees. The algorithm is based on the theory of Paley-Wiener reproducing kernel Hilbert spaces. The paper first studies the fully observable variant, when there are no noises on the observations and only the inputs are random; then it generalizes the ideas to the noisy case using gradient-perturbation methods. Finally, numerical experiments demonstrating both cases are presented.
arXiv.org Artificial Intelligence
Jun-27-2022
- Country:
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Hungary > Budapest
- Budapest (0.05)
- United Kingdom > England
- Europe
- Genre:
- Research Report (0.64)
- Technology: