Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds
Abstract
Gaussian Processes (GPs) are a generic modelling tool for supervised learning. While they have been successfully applied on large datasets, their use in safety-critical applications is hindered by the lack of good performance guarantees. To this end, we propose a method to learn GPs and their sparse approximations by directly optimizing a PAC-Bayesian bound on their generalization performance, instead of maximizing the marginal likelihood. Besides its theoretical appeal, we find in our evaluation that our learning method is robust and yields significantly better generalization guarantees than other common GP approaches on several regression benchmark datasets.
Cite
@article{arxiv.1810.12263,
title = {Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds},
author = {David Reeb and Andreas Doerr and Sebastian Gerwinn and Barbara Rakitsch},
journal= {arXiv preprint arXiv:1810.12263},
year = {2019}
}
Comments
11 pages main text, 12 pages appendix. v2: minor changes, new NeurIPS style file. Final camera-ready version submitted to NeurIPS 2018