Preprint · 2026 · Open access

Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors

Somjit Roy, Prateek Jaiswal, Anirban Bhattacharya, Debdeep Pati, Bani K. Mallick

arXiv (Cornell University) · Published 16 February 2026 · DOI 10.48550/arxiv.2602.14472

Open PDFView at the publisherCite this paper

In brief

“Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors” is a 2026 preprint by Somjit Roy and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
18
Authors
5

Abstract

We study Gaussian Process Thompson Sampling (GP-TS) for sequential decision-making over compact, continuous action spaces and provide a frequentist regret analysis based on fractional Gaussian process posteriors, without relying on domain discretization as in prior work. We show that the variance inflation commonly assumed in existing analyses of GP-TS can be interpreted as Thompson Sampling with respect to a fractional posterior with tempering parameter $α\in (0,1)$. We derive a kernel-agnostic regret bound expressed in terms of the information gain parameter $γ_t$ and the posterior contraction rate $ε_t$, and identify conditions on the Gaussian process prior under which $ε_t$ can be controlled. As special cases of our general bound, we recover regret of order $\tilde{\mathcal{O}}(T^{\frac{1}{2}})$ for the squared exponential kernel, $\tilde{\mathcal{O}}(T^{\frac{2ν+3d}{2(2ν+d)}} )$ for the Matérn-$ν$ kernel, and a bound of order $\tilde{\mathcal{O}}(T^{\frac{2ν+3d}{2(2ν+d)}})$ for the rational quadratic kernel. Overall, our analysis provides a unified and discretization-free regret framework for GP-TS that applies broadly across kernel classes.

Cite this paper

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

APA 7

Roy, S., Jaiswal, P., Bhattacharya, A., Pati, D., & Mallick, B. K. (2026). Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.14472

MLA 9

Roy, Somjit, et al. “Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.14472.

Chicago

Roy, Somjit, Prateek Jaiswal, Anirban Bhattacharya, Debdeep Pati, and Bani K. Mallick. 2026. “Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.14472.

Harvard

Roy, S. et al. (2026) ‘Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors’, arXiv (Cornell University). doi:10.48550/arxiv.2602.14472.

IEEE

S. Roy, P. Jaiswal, A. Bhattacharya, D. Pati, and B. K. Mallick, “Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.14472.

BibTeX

@misc{roy2026frequentist,
  title     = {{Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors}},
  author    = {Roy, Somjit and Jaiswal, Prateek and Bhattacharya, Anirban and Pati, Debdeep and Mallick, Bani K.},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2602.14472},
  url       = {https://doi.org/10.48550/arxiv.2602.14472}
}

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

  • sequential decision making
  • continuous action spaces
  • posterior contraction rates
  • information gain
  • Matérn kernel
  • rational quadratic kernel
  • Gaussian kernel
  • variance inflation

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?

Roy, S., Jaiswal, P., Bhattacharya, A., Pati, D., & Mallick, B. K. (2026). Frequentist Regret Analysis of Gaussian Process Thompson Sampling via Fractional Posteriors. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.14472

How many times has this paper been cited?

1 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?

Somjit Roy, Prateek Jaiswal, Anirban Bhattacharya, Debdeep Pati, Bani K. Mallick.

What is the DOI of this paper?

10.48550/arxiv.2602.14472, permanently at https://doi.org/10.48550/arxiv.2602.14472. 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.