Optimal Kernel Shapes for Local Linear Regression
Abstract
Local linear regression performs very well in many low-dimensional forecasting problems. In high-dimensional spaces, its performance typically decays due to the well-known "curse-of-dimensionality". A possible way to approach this problem is by varying the "shape" of the weighting kernel. In this work we suggest a new, data-driven method to estimating the optimal kernel shape. Experiments us(cid:173) ing an artificially generated data set and data from the UC Irvine repository show the benefits of kernel shaping.
Cite
Text
Ormoneit and Hastie. "Optimal Kernel Shapes for Local Linear Regression." Neural Information Processing Systems, 1999.Markdown
[Ormoneit and Hastie. "Optimal Kernel Shapes for Local Linear Regression." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/ormoneit1999neurips-optimal/)BibTeX
@inproceedings{ormoneit1999neurips-optimal,
title = {{Optimal Kernel Shapes for Local Linear Regression}},
author = {Ormoneit, Dirk and Hastie, Trevor},
booktitle = {Neural Information Processing Systems},
year = {1999},
pages = {540-546},
url = {https://mlanthology.org/neurips/1999/ormoneit1999neurips-optimal/}
}