Preprint · 2023 · Open access

Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds

Shion Takeno, Inatsu, Yu, Masayuki Karasuyama, Ichiro Takeuchi

arXiv (Cornell University) · Published 7 November 2023 · DOI 10.48550/arxiv.2311.03760

Open PDFView at the publisherCite this paper

In brief

“Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds” is a 2023 preprint by Shion Takeno and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 4 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
4
Most cited in
2026 (2)
References
25
Authors
4

Abstract

Among various acquisition functions (AFs) in Bayesian optimization (BO), Gaussian process upper confidence bound (GP-UCB) and Thompson sampling (TS) are well-known options with established theoretical properties regarding Bayesian cumulative regret (BCR). Recently, it has been shown that a randomized variant of GP-UCB achieves a tighter BCR bound compared with GP-UCB, which we call the tighter BCR bound for brevity. Inspired by this study, this paper first shows that TS achieves the tighter BCR bound. On the other hand, GP-UCB and TS often practically suffer from manual hyperparameter tuning and over-exploration issues, respectively. Therefore, we analyze yet another AF called a probability of improvement from the maximum of a sample path (PIMS). We show that PIMS achieves the tighter BCR bound and avoids the hyperparameter tuning, unlike GP-UCB. Furthermore, we demonstrate a wide range of experiments, focusing on the effectiveness of PIMS that mitigates the practical issues of GP-UCB and TS.

Cite this paper

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

APA 7

Takeno, S., Yu, I., Karasuyama, M., & Takeuchi, I. (2023). Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.03760

MLA 9

Takeno, Shion, et al. “Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds.” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2311.03760.

Chicago

Takeno, Shion, Inatsu, Yu, Masayuki Karasuyama, and Ichiro Takeuchi. 2023. “Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.03760.

Harvard

Takeno, S. et al. (2023) ‘Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds’, arXiv (Cornell University). doi:10.48550/arxiv.2311.03760.

IEEE

S. Takeno, I. Yu, M. Karasuyama, and I. Takeuchi, “Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2311.03760.

BibTeX

@misc{takeno2023posterior,
  title     = {{Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds}},
  author    = {Takeno, Shion and Yu, Inatsu, and Karasuyama, Masayuki and Takeuchi, Ichiro},
  howpublished = {arXiv (Cornell University)},
  year      = {2023},
  doi       = {10.48550/arxiv.2311.03760},
  url       = {https://doi.org/10.48550/arxiv.2311.03760}
}

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

Citations by year

YearCitationsShare of the best year
202411
202511
202622

Topic and keywords

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

  • Bayesian optimization
  • acquisition functions
  • Thompson sampling
  • posterior sampling
  • regret bounds
  • hyperparameter 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?

Takeno, S., Yu, I., Karasuyama, M., & Takeuchi, I. (2023). Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.03760

How many times has this paper been cited?

4 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?

Shion Takeno, Inatsu, Yu, Masayuki Karasuyama, Ichiro Takeuchi.

What is the DOI of this paper?

10.48550/arxiv.2311.03760, permanently at https://doi.org/10.48550/arxiv.2311.03760. 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.