Fractal Perturbation of the Nadaraya-Watson Estimator

One of the main tasks in the problems of machine learning and curve fitting is to develop suitable models for given data sets. It requires to generate a function to approximate the data arising from some unknown function. The class of kernel regression estimators is one of main types of nonparametric curve estimations. On the other hand, fractal theory provides new technologies for making complicated irregular curves in many practical problems. In this paper, we are going to investigate fractal curve-fitting problems with the help of kernel regression estimators. For a given data set that arises from an unknown function m, one of the well-known kernel regression estimators, the Nadaraya-Watson estimator m<^>, is applied. We consider the case that m is Holder-continuous of exponent beta with 0 <= 1, and the graph of m is irregular. An estimation for the expectation of ||m<^>-m|(2) is established. Then a fractal perturbation f[m<^>] corresponding to m<^> is constructed to fit the given data. The expectations of ||f[m<^>]-m<^>||(2 )and ||f[m<^>]-m|(2) are also estimated

Automated summary

This paper investigates fractal curve-fitting problems using kernel regression estimators. By applying the Nadaraya-Watson estimator, curve estimation for unknown functions with irregularity is conducted, and an estimation for the expectation is established. Additionally, a fractal perturbation corresponding to the estimator is constructed to fit the given data, with expectations estimated for the perturbation.