DeepAI AI Chat
Log In Sign Up

Nonparametric, Nonasymptotic Confidence Bands with Paley-Wiener Kernels for Band-Limited Functions

by   Balázs Csanád Csáji, et al.
MTA SZTAKI (Institute for Computer Science and Control)

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.


page 1

page 6


Simultaneous confidence bands for nonparametric regression with partially missing covariates

In this paper, we consider a weighted local linear estimator based on th...

A simple approach to construct confidence bands for a regression function with incomplete data

A long-standing problem in the construction of asymptotically correct co...

Nonparametric Confidence Regions for Level Sets: Statistical Properties and Geometry

This paper studies and critically discusses the construction of nonparam...

Adaptation Bounds for Confidence Bands under Self-Similarity

We derive bounds on the scope for a confidence band to adapt to the unkn...

Post-Regularization Confidence Bands for Ordinary Differential Equations

Ordinary differential equation (ODE) is an important tool to study the d...

Asymptotic Confidence Regions for Density Ridges

We develop large sample theory including nonparametric confidence region...