Active sample selection in scalar fields exhibiting non-stationary noise with parametric heteroscedastic Gaussian process regression

Troy Wilson, Stefan B. Williams

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

Abstract

This paper considers the modelling of scalar fields exhibiting non-stationary noise in the context of Gaussian Process (GP) regression. We show how a Heteroscedastic GP produces more accurate predictions of the variance of a process of this type compared to the standard Homoscedastic model. We present a parametric model for the noise process and derive analytical solutions to the Log Marginal Likelihood of the data and its gradients with respect to Hyper Parameters of the kernel and the noise process. We compare our parametric model to one which estimates a full GP for the noise and show analogous predictive performance with a model which has greater computational efficiency and is less complex to implement. We also discuss active sample selection in this framework and show through the numerical simulation of an arrested bathymetric front in an estuary, the superiority of using Mutual Information to Fisher Information, Entropy or Random sampling in terms of errors in the first two moments of the predicted distributions.

Original languageEnglish
Title of host publicationICRA 2017 - IEEE International Conference on Robotics and Automation
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages6455-6462
Number of pages8
ISBN (Electronic)9781509046331
ISBN (Print)9781509046348
DOIs
Publication statusPublished - 21 Jul 2017
Externally publishedYes
Event2017 IEEE International Conference on Robotics and Automation, ICRA 2017 - Singapore, Singapore
Duration: 29 May 20173 Jun 2017

Conference

Conference2017 IEEE International Conference on Robotics and Automation, ICRA 2017
CountrySingapore
CitySingapore
Period29/05/173/06/17

    Fingerprint

Cite this

Wilson, T., & Williams, S. B. (2017). Active sample selection in scalar fields exhibiting non-stationary noise with parametric heteroscedastic Gaussian process regression. In ICRA 2017 - IEEE International Conference on Robotics and Automation (pp. 6455-6462). Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICRA.2017.7989763