Preprint · 2026 · Open access

Exploration strategies for Gaussian process bandit optimization with inference regret guarantees

Hwanwoo Kim, Jungwoo Hong, Kyungjae Lee

arXiv (Cornell University) · Published 12 October 2026 · DOI 10.48550/arxiv.2610.16187

Open PDFView at the publisherCite this paper

In brief

“Exploration strategies for Gaussian process bandit optimization with inference regret guarantees” is a 2026 preprint by Hwanwoo Kim and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
0
References
44
Authors
3

Abstract

Existing cumulative regret guarantees for Bayesian optimization (BO) do not necessarily characterize the quality of the algorithm's final output. This gap is critical under noisy evaluations, where the goal is to return a single high-quality recommendation. To address it, we introduce efficient exploration strategies that can be incorporated into any BO procedure by occasionally replacing the acquisition query with an exploration query. To validate this approach, we bound the Gaussian process posterior standard deviation over the search space via the fill distance of the queries, which measures the largest region left unexplored. We then use this result to derive upper bounds on the inference regret, i.e., the gap between the global optimum and the function value at the algorithm's returned point. Empirically, these exploration strategies improve the final recommendations of existing BO algorithms on synthetic benchmarks, hyperparameter optimization, and a control task.

Cite this paper

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

APA 7

Kim, H., Hong, J., & Lee, K. (2026). Exploration strategies for Gaussian process bandit optimization with inference regret guarantees. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.16187

MLA 9

Kim, Hwanwoo, et al. “Exploration strategies for Gaussian process bandit optimization with inference regret guarantees.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.16187.

Chicago

Kim, Hwanwoo, Jungwoo Hong, and Kyungjae Lee. 2026. “Exploration strategies for Gaussian process bandit optimization with inference regret guarantees.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.16187.

Harvard

Kim, H., Hong, J. and Lee, K. (2026) ‘Exploration strategies for Gaussian process bandit optimization with inference regret guarantees’, arXiv (Cornell University). doi:10.48550/arxiv.2610.16187.

IEEE

H. Kim, J. Hong, and K. Lee, “Exploration strategies for Gaussian process bandit optimization with inference regret guarantees,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.16187.

BibTeX

@misc{kim2026exploration,
  title     = {{Exploration strategies for Gaussian process bandit optimization with inference regret guarantees}},
  author    = {Kim, Hwanwoo and Hong, Jungwoo and Lee, Kyungjae},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.16187},
  url       = {https://doi.org/10.48550/arxiv.2610.16187}
}

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

  • Bayesian optimization
  • exploration strategy
  • fill distance
  • acquisition functions
  • upper bounds
  • hyperparameter optimization
  • control tasks

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?

Kim, H., Hong, J., & Lee, K. (2026). Exploration strategies for Gaussian process bandit optimization with inference regret guarantees. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.16187

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

Who wrote this paper?

Hwanwoo Kim, Jungwoo Hong, Kyungjae Lee.

What is the DOI of this paper?

10.48550/arxiv.2610.16187, permanently at https://doi.org/10.48550/arxiv.2610.16187. 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.