Preprint · 2018 · Open access

Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior

Zi Wang, Beomjoon Kim, Leslie Pack Kaelbling

arXiv (Cornell University) · Published 23 November 2018 · DOI 10.48550/arxiv.1811.09558

Open PDFView at the publisherCite this paper

In brief

“Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior” is a 2018 preprint by Zi Wang and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 30 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
30
Most cited in
2020 (8)
References
48
Authors
3

Abstract

Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and probability of improvement achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as the number of offline data and the number of online evaluations increase. Empirically, we have verified our approach on challenging simulated robotic problems featuring task and motion planning.

Cite this paper

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

APA 7

Wang, Z., Kim, B., & Kaelbling, L. P. (2018). Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1811.09558

MLA 9

Wang, Zi, et al. “Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior.” arXiv (Cornell University), 2018. https://doi.org/10.48550/arxiv.1811.09558.

Chicago

Wang, Zi, Beomjoon Kim, and Leslie Pack Kaelbling. 2018. “Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1811.09558.

Harvard

Wang, Z., Kim, B. and Kaelbling, L. P. (2018) ‘Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior’, arXiv (Cornell University). doi:10.48550/arxiv.1811.09558.

IEEE

Z. Wang, B. Kim, and L. P. Kaelbling, “Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior,” arXiv (Cornell University), 2018, doi: 10.48550/arxiv.1811.09558.

BibTeX

@misc{wang2018regret,
  title     = {{Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior}},
  author    = {Wang, Zi and Kim, Beomjoon and Kaelbling, Leslie Pack},
  howpublished = {arXiv (Cornell University)},
  year      = {2018},
  doi       = {10.48550/arxiv.1811.09558},
  url       = {https://doi.org/10.48550/arxiv.1811.09558}
}

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

Citations by year

YearCitationsShare of the best year
201822
201911
202088
202133
202244
202333
202477
202522

Topic and keywords

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

  • Bayesian optimization
  • regret bounds
  • Gaussian process priors
  • empirical Bayes
  • offline data
  • probability of improvement
  • measurement noise
  • task and motion planning

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?

Wang, Z., Kim, B., & Kaelbling, L. P. (2018). Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1811.09558

How many times has this paper been cited?

30 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?

Zi Wang, Beomjoon Kim, Leslie Pack Kaelbling.

What is the DOI of this paper?

10.48550/arxiv.1811.09558, permanently at https://doi.org/10.48550/arxiv.1811.09558. 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.