Abstract
In this chapter we describe a class of regression techniques that achieve flexibility in estimating the regression function f(X) over the domain ℝP by fitting a different but simple model separately at each query point x 0. This is done by using only those observations close to the target point x 0 to fit the simple model, and in such a way that the resulting estimated function \( \hat f\left( X \right)\)(X) is smooth in ℝP. This localization is achieved via a weighting function or kernel K ⋋(x 0, x i ), which assigns a weight to x i based on its distance from x 0. The kernels K ⋋ are typically indexed by a parameter ⋋ that dictates the width of the neighborhood. These memory-based methods require in principle little or no training; all the work gets done at evaluation time. The only parameter that needs to be determined from the training data is ⋋. The model, however, is the entire training data set.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer Science+Business Media New York
About this chapter
Cite this chapter
Hastie, T., Friedman, J., Tibshirani, R. (2001). Kernel Methods. In: The Elements of Statistical Learning. Springer Series in Statistics. Springer, New York, NY. https://doi.org/10.1007/978-0-387-21606-5_6
Download citation
DOI: https://doi.org/10.1007/978-0-387-21606-5_6
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4899-0519-2
Online ISBN: 978-0-387-21606-5
eBook Packages: Springer Book Archive