Dissertation · 2026 · Open access

Bayesian robust optimization

Hoai Phuong Le

Warwick Research Archive Portal (University of Warwick) · Published 17 September 2026 · DOI 10.82444/warw.33908326

Open full textCite this paper

In brief

“Bayesian robust optimization” is a 2026 dissertation by Hoai Phuong Le, published in Warwick Research Archive Portal (University of Warwick). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at University of Warwick.

Citations
0
Authors
1

Abstract

When optimizing complex systems, the implemented solution can often not be guaranteed to exactly follow the design specification, or there is uncertainty about the environment in which the solution operates. In such cases, one is often looking for solutions that are not merely good but also robust. Robustness in this context means some degree of insensitivity to small disturbances of the environment or the design variables. In this thesis, we are optimizing the expected performance of a solution given disturbances of the input and noise on the output. Bayesian optimization is used throughout the thesis. Based on the well-known Knowledge Gradient acquisition function, we first develop a novel acquisition function for searching robust solutions of black-box objectives. We also study a naive method for finding robust solutions by approximating the robustness measure directly. Furthermore, we consider reliability, which is often critical in engineering. We next examine how these two methods work in the case of uncertain input when the input may be uncontrollable and unobservable. We propose some improvements to the latter method and compare with the former one under uncertain inputs. We then extend our novel method to multiobjective optimization of two independent objectives and apply it to a real-world problem. In addition, we derive the analytical formulas for mean and variance of the robustness measure and consider both when optimizing their linear combination. Finally, we focus on studying one important stage of Bayesian optimization: optimizing the acquisition function. We examine the landscapes and the difficulty of optimizing two popular acquisition functions: Expected Improvement and Knowledge Gradient, and propose a transfer learning method with the aim of improving the quality of optimization.

Cite this paper

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

APA 7

Le, H. P. (2026). Bayesian robust optimization. Warwick Research Archive Portal (University of Warwick). https://doi.org/10.82444/warw.33908326

MLA 9

Le, Hoai Phuong. “Bayesian robust optimization.” Warwick Research Archive Portal (University of Warwick), 2026. https://doi.org/10.82444/warw.33908326.

Chicago

Le, Hoai Phuong. 2026. “Bayesian robust optimization.” Warwick Research Archive Portal (University of Warwick). https://doi.org/10.82444/warw.33908326.

Harvard

Le, H. P. (2026) ‘Bayesian robust optimization’, Warwick Research Archive Portal (University of Warwick). doi:10.82444/warw.33908326.

IEEE

H. P. Le, “Bayesian robust optimization,” Warwick Research Archive Portal (University of Warwick), 2026, doi: 10.82444/warw.33908326.

BibTeX

@phdthesis{le2026bayesian,
  title     = {{Bayesian robust optimization}},
  author    = {Le, Hoai Phuong},
  year      = {2026},
  doi       = {10.82444/warw.33908326},
  url       = {https://doi.org/10.82444/warw.33908326}
}

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

Topic and keywords

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

  • robustness metrics
  • acquisition functions
  • knowledge gradient
  • expected improvement
  • black-box optimization
  • uncertain inputs
  • reliability
  • multi-objective 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?

Le, H. P. (2026). Bayesian robust optimization. Warwick Research Archive Portal (University of Warwick). https://doi.org/10.82444/warw.33908326

How many times has this paper been cited?

0 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 University of Warwick: sign in and open the full text from this page.

Who wrote this paper?

Hoai Phuong Le.

What is the DOI of this paper?

10.82444/warw.33908326, permanently at https://doi.org/10.82444/warw.33908326. 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.