Asymptotic Analysis of the Learning Curve for Gaussian Process Regression
Abstract
This paper deals with the learning curve in a Gaussian process regression framework. The learning curve describes the generalization error of the Gaussian process used for the regression. The main result is the proof of a theorem giving the generalization error for a large class of correlation kernels and for any dimension when the number of observations is large. From this theorem, we can deduce the asymptotic behavior of the generalization error when the observation error is small. The presented proof generalizes previous ones that were limited to special kernels or to small dimensions (one or two). The theoretical results are applied to a nuclear safety problem.
Cite
Text
Le Gratiet and Garnier. "Asymptotic Analysis of the Learning Curve for Gaussian Process Regression." Machine Learning, 2015. doi:10.1007/S10994-014-5437-0Markdown
[Le Gratiet and Garnier. "Asymptotic Analysis of the Learning Curve for Gaussian Process Regression." Machine Learning, 2015.](https://mlanthology.org/mlj/2015/gratiet2015mlj-asymptotic/) doi:10.1007/S10994-014-5437-0BibTeX
@article{gratiet2015mlj-asymptotic,
title = {{Asymptotic Analysis of the Learning Curve for Gaussian Process Regression}},
author = {Le Gratiet, Loïc and Garnier, Josselin},
journal = {Machine Learning},
year = {2015},
pages = {407-433},
doi = {10.1007/S10994-014-5437-0},
volume = {98},
url = {https://mlanthology.org/mlj/2015/gratiet2015mlj-asymptotic/}
}