Preprint · 2018 · Open access

Maximizing acquisition functions for Bayesian optimization

Wilson, James T., Frank Hutter, Marc Peter Deisenroth

arXiv (Cornell University), 31, 9884–9895 · Published 25 May 2018 · DOI 10.48550/arxiv.1805.10196

Open PDFView at the publisherCite this paper

In brief

“Maximizing acquisition functions for Bayesian optimization” is a 2018 preprint by Wilson, James T. and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 295 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
295
Most cited in
2025 (55)
References
69
Authors
3

Abstract

Bayesian optimization is a sample-efficient approach to global optimization that relies on theoretically motivated value heuristics (acquisition functions) to guide its search process. Fully maximizing acquisition functions produces the Bayes' decision rule, but this ideal is difficult to achieve since these functions are frequently non-trivial to optimize. This statement is especially true when evaluating queries in parallel, where acquisition functions are routinely non-convex, high-dimensional, and intractable. We first show that acquisition functions estimated via Monte Carlo integration are consistently amenable to gradient-based optimization. Subsequently, we identify a common family of acquisition functions, including EI and UCB, whose properties not only facilitate but justify use of greedy approaches for their maximization.

Cite this paper

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

APA 7

T., W. J., Hutter, F., & Deisenroth, M. P. (2018). Maximizing acquisition functions for Bayesian optimization. arXiv (Cornell University), 31, 9884–9895. https://doi.org/10.48550/arxiv.1805.10196

MLA 9

T., Wilson, James, et al. “Maximizing acquisition functions for Bayesian optimization.” arXiv (Cornell University), vol. 31, 2018, pp. 9884–9895. https://doi.org/10.48550/arxiv.1805.10196.

Chicago

T., Wilson, James, Frank Hutter, and Marc Peter Deisenroth. 2018. “Maximizing acquisition functions for Bayesian optimization.” arXiv (Cornell University) 31: 9884–9895. https://doi.org/10.48550/arxiv.1805.10196.

Harvard

T., W. J., Hutter, F. and Deisenroth, M. P. (2018) ‘Maximizing acquisition functions for Bayesian optimization’, arXiv (Cornell University), 31, pp. 9884–9895. doi:10.48550/arxiv.1805.10196.

IEEE

W. J. T., F. Hutter, and M. P. Deisenroth, “Maximizing acquisition functions for Bayesian optimization,” arXiv (Cornell University), vol. 31, pp. 9884–9895, 2018, doi: 10.48550/arxiv.1805.10196.

BibTeX

@misc{t2018maximizing,
  title     = {{Maximizing acquisition functions for Bayesian optimization}},
  author    = {T., Wilson, James and Hutter, Frank and Deisenroth, Marc Peter},
  howpublished = {arXiv (Cornell University)},
  year      = {2018},
  volume    = {31},
  pages     = {9884--9895},
  doi       = {10.48550/arxiv.1805.10196},
  url       = {https://doi.org/10.48550/arxiv.1805.10196}
}

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

Citations by year

YearCitationsShare of the best year
201833
20191111
20202626
20214242
20223939
20234040
20243838
20255555
20264141

Topic and keywords

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

  • Bayesian optimization
  • acquisition functions
  • Monte Carlo estimation
  • gradient-based optimization
  • expected improvement
  • upper confidence bound
  • greedy optimization
  • parallel query processing

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?

T., W. J., Hutter, F., & Deisenroth, M. P. (2018). Maximizing acquisition functions for Bayesian optimization. arXiv (Cornell University), 31, 9884–9895. https://doi.org/10.48550/arxiv.1805.10196

How many times has this paper been cited?

295 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Wilson, James T., Frank Hutter, Marc Peter Deisenroth.

What is the DOI of this paper?

10.48550/arxiv.1805.10196, permanently at https://doi.org/10.48550/arxiv.1805.10196. 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.