Preprint · 2017 · Open access

Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization

Nikitas Rontsis, Michael A. Osborne, Paul J. Goulart

arXiv (Cornell University) · Published 13 July 2017 · DOI 10.48550/arxiv.1707.04191

Open PDFView at the publisherCite this paper

In brief

“Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization” is a 2017 preprint by Nikitas Rontsis and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 7 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
7
Most cited in
2020 (2)
References
24
Authors
3

Abstract

We propose a novel, theoretically-grounded, acquisition function for Batch Bayesian optimization informed by insights from distributionally ambiguous optimization. Our acquisition function is a lower bound on the well-known Expected Improvement function, which requires evaluation of a Gaussian Expectation over a multivariate piecewise affine function. Our bound is computed instead by evaluating the best-case expectation over all probability distributions consistent with the same mean and variance as the original Gaussian distribution. Unlike alternative approaches, including Expected Improvement, our proposed acquisition function avoids multi-dimensional integrations entirely, and can be computed exactly - even on large batch sizes - as the solution of a tractable convex optimization problem. Our suggested acquisition function can also be optimized efficiently, since first and second derivative information can be calculated inexpensively as by-products of the acquisition function calculation itself. We derive various novel theorems that ground our work theoretically and we demonstrate superior performance via simple motivating examples, benchmark functions and real-world problems.

Cite this paper

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

APA 7

Rontsis, N., Osborne, M. A., & Goulart, P. J. (2017). Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1707.04191

MLA 9

Rontsis, Nikitas, et al. “Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1707.04191.

Chicago

Rontsis, Nikitas, Michael A. Osborne, and Paul J. Goulart. 2017. “Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1707.04191.

Harvard

Rontsis, N., Osborne, M. A. and Goulart, P. J. (2017) ‘Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization’, arXiv (Cornell University). doi:10.48550/arxiv.1707.04191.

IEEE

N. Rontsis, M. A. Osborne, and P. J. Goulart, “Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1707.04191.

BibTeX

@misc{rontsis2017distributionally,
  title     = {{Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization}},
  author    = {Rontsis, Nikitas and Osborne, Michael A. and Goulart, Paul J.},
  howpublished = {arXiv (Cornell University)},
  year      = {2017},
  doi       = {10.48550/arxiv.1707.04191},
  url       = {https://doi.org/10.48550/arxiv.1707.04191}
}

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

Citations by year

YearCitationsShare of the best year
201811
201911
202022
202111
202211
202411

Topic and keywords

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

  • batch Bayesian optimization
  • acquisition functions
  • expected improvement
  • lower bounds
  • convex optimization
  • derivative computation
  • distributionally robust optimization

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?

Rontsis, N., Osborne, M. A., & Goulart, P. J. (2017). Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1707.04191

How many times has this paper been cited?

7 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?

Nikitas Rontsis, Michael A. Osborne, Paul J. Goulart.

What is the DOI of this paper?

10.48550/arxiv.1707.04191, permanently at https://doi.org/10.48550/arxiv.1707.04191. 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.