Optimality of Cross-validation in Scattered Data Approximation

05/28/2021
by   Felix Bartel, et al.
0

Choosing models from a hypothesis space is a frequent task in approximation theory and inverse problems. Cross-validation is a classical tool in the learner's repertoire to compare the goodness of fit for different reconstruction models. Much work has been dedicated to computing this quantity in a fast manner but tackling its theoretical properties occurs to be difficult. So far, most optimality results are stated in an asymptotic fashion. In this paper we propose a concentration inequality on the difference of cross-validation score and the risk functional with respect to the squared error. This gives a pre-asymptotic bound which holds with high probability. For the assumptions we rely on bounds on the uniform error of the model which allow for a broadly applicable framework. We support our claims by applying this machinery to Shepard's model, where we are able to determine precise constants of the concentration inequality. Numerical experiments in combination with fast algorithms indicate the applicability of our results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/14/2023

A fast surrogate cross validation algorithm for meshfree RBF collocation approaches

Cross validation is an important tool in the RBF collocation setting, es...
research
04/04/2019

Cross-Validation for Correlated Data

K-fold cross-validation (CV) with squared error loss is widely used for ...
research
06/19/2017

An a Priori Exponential Tail Bound for k-Folds Cross-Validation

We consider a priori generalization bounds developed in terms of cross-v...
research
11/04/2022

Concentration inequalities for leave-one-out cross validation

In this article we prove that estimator stability is enough to show that...
research
11/21/2021

A stochastic extended Rippa's algorithm for LpOCV

In kernel-based approximation, the tuning of the so-called shape paramet...
research
12/27/2019

Statistical Agnostic Mapping: a Framework in Neuroimaging based on Concentration Inequalities

In the 70s a novel branch of statistics emerged focusing its effort in s...
research
09/11/2019

Aggregated Hold-Out

Aggregated hold-out (Agghoo) is a method which averages learning rules s...

Please sign up or login with your details

Forgot password? Click here to reset