Please use this identifier to cite or link to this item:
Title: How priors of initial hyperparameters affect Gaussian process regression models
Authors: Chen, Zexun
Wang, Bo
First Published: 1-Nov-2017
Publisher: Elsevier
Citation: Neurocomputing, 2017
Abstract: The hyperparameters in Gaussian process regression (GPR) model with a specified kernel are often estimated from the data via the maximum marginal likelihood. Due to the non-convexity of marginal likelihood with respect to the hyperparameters, the optimisation may not converge to the global maxima. A common approach to tackle this issue is to use multiple starting points randomly selected from a specific prior distribution. As a result the choice of prior distribution may play a vital role in the predictability of this approach. However, there exists little research in the literature to study the impact of the prior distributions on the hyperparameter estimation and the performance of GPR. In this paper, we provide the first empirical study on this problem using simulated and real data experiments. We consider different types of priors for the initial values of hyperparameters for some commonly used kernels and investigate the influence of the priors on the predictability of GPR models. The results reveal that, once a kernel is chosen, different priors for the initial hyperparameters have no significant impact on the performance of GPR prediction, despite that the estimates of the hyperparameters are very different to the true values in some cases.
DOI Link: 10.1016/j.neucom.2017.10.028
ISSN: 0925-2312
Embargo on file until: 1-Nov-2018
Version: Post-print
Status: Peer-reviewed
Type: Journal Article
Rights: Copyright © 2017, Elsevier. Deposited with reference to the publisher’s open access archiving policy.
Description: The file associated with this record is under embargo until 12 months after publication, in accordance with the publisher's self-archiving policy. The full text may be available through the publisher links provided above.
Appears in Collections:Published Articles, Dept. of Mathematics

Files in This Item:
File Description SizeFormat 
Accepted-Version.pdfPost-review (final submitted author manuscript)173.8 kBAdobe PDFView/Open

Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.