Achieving robustness to aleatoric uncertainty with heteroscedastic Bayesian optimisation
Authors
A Aldrick, Alexander
Garcia-Ortegon, Miguel
Lalchand, Vidhi
Lee, Alpha A
Publication Date
2021-11-24Journal Title
Machine Learning: Science and Technology
Publisher
IOP Publishing
Volume
3
Issue
1
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Griffiths, R., A Aldrick, A., Garcia-Ortegon, M., Lalchand, V., & Lee, A. A. (2021). Achieving robustness to aleatoric uncertainty with heteroscedastic Bayesian optimisation. Machine Learning: Science and Technology, 3 (1) https://doi.org/10.1088/2632-2153/ac298c
Abstract
Abstract: Bayesian optimisation is a sample-efficient search methodology that holds great promise for accelerating drug and materials discovery programs. A frequently-overlooked modelling consideration in Bayesian optimisation strategies however, is the representation of heteroscedastic aleatoric uncertainty. In many practical applications it is desirable to identify inputs with low aleatoric noise, an example of which might be a material composition which displays robust properties in response to a noisy fabrication process. In this paper, we propose a heteroscedastic Bayesian optimisation scheme capable of representing and minimising aleatoric noise across the input space. Our scheme employs a heteroscedastic Gaussian process surrogate model in conjunction with two straightforward adaptations of existing acquisition functions. First, we extend the augmented expected improvement heuristic to the heteroscedastic setting and second, we introduce the aleatoric noise-penalised expected improvement (ANPEI) heuristic. Both methodologies are capable of penalising aleatoric noise in the suggestions. In particular, the ANPEI acquisition yields improved performance relative to homoscedastic Bayesian optimisation and random sampling on toy problems as well as on two real-world scientific datasets. Code is available at: https://github.com/Ryan-Rhys/Heteroscedastic-BO
Keywords
Paper, Bayesian optimisation, Gaussian processes, heteroscedasticity
Identifiers
mlstac298c, ac298c, mlst-100414.r1
External DOI: https://doi.org/10.1088/2632-2153/ac298c
This record's URL: https://www.repository.cam.ac.uk/handle/1810/330992
Rights
Licence:
http://creativecommons.org/licenses/by/4.0
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.