Conference paper · 2021 · Open access

How Bayesian should Bayesian optimisation be?

George De Ath, Richard Everson, Jonathan Edward Fieldsend

Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 1860–1869 · Published 7 July 2021 · DOI 10.1145/3449726.3463164

Open PDFView at the publisherCite this paper

In brief

“How Bayesian should Bayesian optimisation be?” is a 2021 conference paper by George De Ath and 2 co-authors, published in Genetic and Evolutionary Computation Conference Companion (GECCO Companion). OpenAlex counts 16 citations as of 19 November 2026, which puts it in the top 8% of works published in 2021 by citations. It is open access: the full text is free to read at Genetic and Evolutionary Computation Conference Companion (GECCO Companion).

Citations
16
Most cited in
2026 (5)
Field-weighted impact
2.08
References
72
Authors
3

Abstract

Bayesian optimisation (BO) uses probabilistic surrogate models - usually Gaussian processes (GPs) - for the optimisation of expensive black-box functions. At each BO iteration, the GP hyperparameters are fit to previously-evaluated data by maximising the marginal likelihood. However, this fails to account for uncertainty in the hyperparameters themselves, leading to overconfident model predictions. This uncertainty can be accounted for by taking the Bayesian approach of marginalising out the model hyperparameters. We investigate whether a fully-Bayesian treatment of the Gaussian process hyperparameters in BO (FBBO) leads to improved optimisation performance. Since an analytic approach is intractable, we compare FBBO using three approximate inference schemes to the maximum likelihood approach, using the Expected Improvement (EI) and Upper Confidence Bound (UCB) acquisition functions paired with ARD and isotropic Matérn kernels, across 15 well-known benchmark problems for 4 observational noise settings. FBBO using EI with an ARD kernel leads to the best performance in the noise-free setting, with much less difference between combinations of BO components when the noise is increased. FBBO leads to over-exploration with UCB, but is not detrimental with EI. Therefore, we recommend that FBBO using EI with an ARD kernel as the default choice for BO.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

De Ath, G., Everson, R., & Fieldsend, J. E. (2021). How Bayesian should Bayesian optimisation be? Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 1860–1869. https://doi.org/10.1145/3449726.3463164

MLA 9

De Ath, George, et al. “How Bayesian should Bayesian optimisation be?” Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 2021, pp. 1860–1869. https://doi.org/10.1145/3449726.3463164.

Chicago

De Ath, George, Richard Everson, and Jonathan Edward Fieldsend. 2021. “How Bayesian should Bayesian optimisation be?” Genetic and Evolutionary Computation Conference Companion (GECCO Companion): 1860–1869. https://doi.org/10.1145/3449726.3463164.

Harvard

De Ath, G., Everson, R. and Fieldsend, J. E. (2021) ‘How Bayesian should Bayesian optimisation be?’, Genetic and Evolutionary Computation Conference Companion (GECCO Companion), pp. 1860–1869. doi:10.1145/3449726.3463164.

IEEE

G. De Ath, R. Everson, and J. E. Fieldsend, “How Bayesian should Bayesian optimisation be?,” Genetic and Evolutionary Computation Conference Companion (GECCO Companion), pp. 1860–1869, 2021, doi: 10.1145/3449726.3463164.

BibTeX

@inproceedings{death2021bayesian,
  title     = {{How Bayesian should Bayesian optimisation be?}},
  author    = {De Ath, George and Everson, Richard and Fieldsend, Jonathan Edward},
  booktitle = {Genetic and Evolutionary Computation Conference Companion (GECCO Companion)},
  year      = {2021},
  pages     = {1860--1869},
  doi       = {10.1145/3449726.3463164},
  url       = {https://doi.org/10.1145/3449726.3463164}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202233
202322
202422
202544
202655

Its field-weighted citation impact is 2.08: it has been cited 2.08 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research

  • Bayesian optimization
  • marginal likelihood
  • Matérn kernel
  • measurement noise
  • expensive black-box functions

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

De Ath, G., Everson, R., & Fieldsend, J. E. (2021). How Bayesian should Bayesian optimisation be? Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 1860–1869. https://doi.org/10.1145/3449726.3463164

How many times has this paper been cited?

16 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Genetic and Evolutionary Computation Conference Companion (GECCO Companion): sign in and open the PDF from this page.

Who wrote this paper?

George De Ath, Richard Everson, Jonathan Edward Fieldsend.

What is the DOI of this paper?

10.1145/3449726.3463164, permanently at https://doi.org/10.1145/3449726.3463164. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.