Fast methods for training Gaussian processes on large datasets

Moore, C.J., Chua, A.J.K., Berry, C.P.L. and Gair, J.R. (2016) Fast methods for training Gaussian processes on large datasets. Royal Society Open Science, 3(5), 160125. (doi: 10.1098/rsos.160125)

[img] Text
218919.pdf - Published Version
Available under License Creative Commons Attribution.



Gaussian process regression (GPR) is a non-parametric Bayesian technique for interpolating or fitting data. The main barrier to further uptake of this powerful tool rests in the computational costs associated with the matrices which arise when dealing with large datasets. Here, we derive some simple results which we have found useful for speeding up the learning stage in the GPR algorithm, and especially for performing Bayesian model comparison between different covariance functions. We apply our techniques to both synthetic and real data and quantify the speed-up relative to using nested sampling to numerically evaluate model evidences.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Gair, Dr Jonathan and Berry, Dr Christopher
Authors: Moore, C.J., Chua, A.J.K., Berry, C.P.L., and Gair, J.R.
College/School:College of Science and Engineering > School of Physics and Astronomy
Journal Name:Royal Society Open Science
Publisher:The Royal Society
ISSN (Online):2054-5703
Copyright Holders:Copyright © 2016 The Authors
First Published:First published in 3(5):160125
Publisher Policy:Reproduced under a Creative Commons licence
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record