Guarnizo, C. and Alvarez Lopez, M.A. orcid.org/0000-0002-8980-4472 (2018) Fast kernel approximations for latent force models and convolved multiple-output Gaussian processes. In: Uncertainty in Artificial Intelligence: Proceedings of the Thirty-Fourth Conference (2018). Uncertainty in Artificial Intelligence 2018, 06-10 Aug 2018, Monterey, California, USA. AUAI Press ISBN 978-0-9966431-3-9
Abstract
A latent force model is a Gaussian process with a covariance function inspired by a differential operator. Such covariance function is obtained by performing convolution integrals between Green's functions associated to the differential operators, and covariance functions associated to latent functions. In the classical formulation of latent force models, the covariance functions are obtained analytically by solving a double integral, leading to expressions that involve numerical solutions of different types of error functions. In consequence, the covariance matrix calculation is considerably expensive, because it requires the evaluation of one or more of these error functions. In this paper, we use random Fourier features to approximate the solution of these double integrals obtaining simpler analytical expressions for such covariance functions. We show experimental results using ordinary differential operators and provide an extension to build general kernel functions for convolved multiple output Gaussian processes.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2018 AUAI Press. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL (EPSRC) EP/N014162/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 12 Jun 2018 14:27 |
Last Modified: | 16 Jan 2019 15:53 |
Published Version: | http://auai.org/uai2018/proceedings/papers/295.pdf |
Status: | Published |
Publisher: | AUAI Press |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:131926 |