String Gaussian Process Kernels
Machine Learning
2015-06-09 v1
Abstract
We introduce a new class of nonstationary kernels, which we derive as covariance functions of a novel family of stochastic processes we refer to as string Gaussian processes (string GPs). We construct string GPs to allow for multiple types of local patterns in the data, while ensuring a mild global regularity condition. In this paper, we illustrate the efficacy of the approach using synthetic data and demonstrate that the model outperforms competing approaches on well studied, real-life datasets that exhibit nonstationary features.
Cite
@article{arxiv.1506.02239,
title = {String Gaussian Process Kernels},
author = {Yves-Laurent Kom Samo and Stephen Roberts},
journal= {arXiv preprint arXiv:1506.02239},
year = {2015}
}