English

EigenGP: Sparse Gaussian process models with data-dependent eigenfunctions

Machine Learning 2013-03-15 v3 Computation Machine Learning

Abstract

Gaussian processes (GPs) provide a nonparametric representation of functions. However, classical GP inference suffers from high computational cost and it is difficult to design nonstationary GP priors in practice. In this paper, we propose a sparse Gaussian process model, EigenGP, based on the Karhunen-Loeve (KL) expansion of a GP prior. We use the Nystrom approximation to obtain data dependent eigenfunctions and select these eigenfunctions by evidence maximization. This selection reduces the number of eigenfunctions in our model and provides a nonstationary covariance function. To handle nonlinear likelihoods, we develop an efficient expectation propagation (EP) inference algorithm, and couple it with expectation maximization for eigenfunction selection. Because the eigenfunctions of a Gaussian kernel are associated with clusters of samples - including both the labeled and unlabeled - selecting relevant eigenfunctions enables EigenGP to conduct semi-supervised learning. Our experimental results demonstrate improved predictive performance of EigenGP over alternative state-of-the-art sparse GP and semisupervised learning methods for regression, classification, and semisupervised classification.

Keywords

Cite

@article{arxiv.1204.3972,
  title  = {EigenGP: Sparse Gaussian process models with data-dependent eigenfunctions},
  author = {Yuan Qi and Bo Dai and Yao Zhu},
  journal= {arXiv preprint arXiv:1204.3972},
  year   = {2013}
}

Comments

10 pages, 19 figures

R2 v1 2026-06-21T20:51:11.054Z