Preprint · 2025 · Open access

A Broader View of Thompson Sampling

Qu, Yanlin, Hongseok Namkoong, Assaf J. Zeevi

arXiv (Cornell University) · Published 8 October 2025 · DOI 10.48550/arxiv.2510.07208

Open PDFView at the publisherCite this paper

In brief

“A Broader View of Thompson Sampling” is a 2025 preprint by Qu, Yanlin and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 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
0
References
16
Authors
3

Abstract

Thompson Sampling is one of the most widely used and studied bandit algorithms, known for its simple structure, low regret performance, and solid theoretical guarantees. Yet, in stark contrast to most other families of bandit algorithms, the exact mechanism through which posterior sampling (as introduced by Thompson) is able to "properly" balance exploration and exploitation, remains a mystery. In this paper, we show that the core insight to address this question stems from recasting Thompson Sampling as an online optimization algorithm. To distill this, we introduce a suitable time invariant notion of regret that leads to a stationarized bandit problem, and a stationary Bellman-optimal policy. We then show that Thompson Sampling admits an online optimization form that mimics the structure of the aforementioned Bellman-optimal policy, where "greediness" is regularized by a measure of residual uncertainty. This new lens of online optimization allows both a better understanding of Thompson Sampling dynamics, as well as a principled manner for policy improvement that mimics the Bellman-optimal benchmark.

Cite this paper

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

APA 7

Yanlin, Q., Namkoong, H., & Zeevi, A. J. (2025). A Broader View of Thompson Sampling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.07208

MLA 9

Yanlin, Qu,, et al. “A Broader View of Thompson Sampling.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2510.07208.

Chicago

Yanlin, Qu,, Hongseok Namkoong, and Assaf J. Zeevi. 2025. “A Broader View of Thompson Sampling.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.07208.

Harvard

Yanlin, Q., Namkoong, H. and Zeevi, A. J. (2025) ‘A Broader View of Thompson Sampling’, arXiv (Cornell University). doi:10.48550/arxiv.2510.07208.

IEEE

Q. Yanlin, H. Namkoong, and A. J. Zeevi, “A Broader View of Thompson Sampling,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2510.07208.

BibTeX

@misc{yanlin2025broader,
  title     = {{A Broader View of Thompson Sampling}},
  author    = {Yanlin, Qu, and Namkoong, Hongseok and Zeevi, Assaf J.},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2510.07208},
  url       = {https://doi.org/10.48550/arxiv.2510.07208}
}

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

  • Thompson sampling
  • multi-armed bandits
  • exploration-exploitation balance
  • online optimization
  • regret
  • residual uncertainty
  • policy improvement
  • posterior sampling

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?

Yanlin, Q., Namkoong, H., & Zeevi, A. J. (2025). A Broader View of Thompson Sampling. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.07208

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?

Qu, Yanlin, Hongseok Namkoong, Assaf J. Zeevi.

What is the DOI of this paper?

10.48550/arxiv.2510.07208, permanently at https://doi.org/10.48550/arxiv.2510.07208. 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.