Preprint · 2018 · Open access

Adversarially Robust Optimization with Gaussian Processes

Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher

arXiv (Cornell University), 31, 5760–5770 · Published 25 October 2018 · DOI 10.48550/arxiv.1810.10775

Open PDFView at the publisherCite this paper

In brief

“Adversarially Robust Optimization with Gaussian Processes” is a 2018 preprint by Ilija Bogunovic and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 132 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
132
Most cited in
2021 (23)
References
25
Authors
4

Abstract

In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturbation. This problem is motivated by settings in which the underlying functions during optimization and implementation stages are different, or when one is interested in finding an entire region of good inputs rather than only a single point. We show that standard GP optimization algorithms do not exhibit the desired robustness properties, and provide a novel confidence-bound based algorithm StableOpt for this purpose. We rigorously establish the required number of samples for StableOpt to find a near-optimal point, and we complement this guarantee with an algorithm-independent lower bound. We experimentally demonstrate several potential applications of interest using real-world data sets, and we show that StableOpt consistently succeeds in finding a stable maximizer where several baseline methods fail.

Cite this paper

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

APA 7

Bogunovic, I., Scarlett, J., Jegelka, S., & Cevher, V. (2018). Adversarially Robust Optimization with Gaussian Processes. arXiv (Cornell University), 31, 5760–5770. https://doi.org/10.48550/arxiv.1810.10775

MLA 9

Bogunovic, Ilija, et al. “Adversarially Robust Optimization with Gaussian Processes.” arXiv (Cornell University), vol. 31, 2018, pp. 5760–5770. https://doi.org/10.48550/arxiv.1810.10775.

Chicago

Bogunovic, Ilija, Jonathan Scarlett, Stefanie Jegelka, and Volkan Cevher. 2018. “Adversarially Robust Optimization with Gaussian Processes.” arXiv (Cornell University) 31: 5760–5770. https://doi.org/10.48550/arxiv.1810.10775.

Harvard

Bogunovic, I. et al. (2018) ‘Adversarially Robust Optimization with Gaussian Processes’, arXiv (Cornell University), 31, pp. 5760–5770. doi:10.48550/arxiv.1810.10775.

IEEE

I. Bogunovic, J. Scarlett, S. Jegelka, and V. Cevher, “Adversarially Robust Optimization with Gaussian Processes,” arXiv (Cornell University), vol. 31, pp. 5760–5770, 2018, doi: 10.48550/arxiv.1810.10775.

BibTeX

@misc{bogunovic2018adversarially,
  title     = {{Adversarially Robust Optimization with Gaussian Processes}},
  author    = {Bogunovic, Ilija and Scarlett, Jonathan and Jegelka, Stefanie and Cevher, Volkan},
  howpublished = {arXiv (Cornell University)},
  year      = {2018},
  volume    = {31},
  pages     = {5760--5770},
  doi       = {10.48550/arxiv.1810.10775},
  url       = {https://doi.org/10.48550/arxiv.1810.10775}
}

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

Citations by year

YearCitationsShare of the best year
201988
20201717
20212323
20222121
20232323
20241414
20251818
202688

Topic and keywords

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

  • adversarial robustness
  • Gaussian process optimization
  • confidence limits
  • sample complexity
  • lower bounds

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?

Bogunovic, I., Scarlett, J., Jegelka, S., & Cevher, V. (2018). Adversarially Robust Optimization with Gaussian Processes. arXiv (Cornell University), 31, 5760–5770. https://doi.org/10.48550/arxiv.1810.10775

How many times has this paper been cited?

132 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?

Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher.

What is the DOI of this paper?

10.48550/arxiv.1810.10775, permanently at https://doi.org/10.48550/arxiv.1810.10775. 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.