Conference paper · 2014 · Open access

Prior-free and prior-dependent regret bounds for Thompson Sampling

Sébastien Bubeck, Che-Yu Liu

Conference on Information Sciences and Systems, 26, 1–9 · Published 1 March 2014 · DOI 10.1109/ciss.2014.6814158

Open PDFView at the publisherCite this paper

In brief

“Prior-free and prior-dependent regret bounds for Thompson Sampling” is a 2014 conference paper by Sébastien Bubeck and Che-Yu Liu, published in Conference on Information Sciences and Systems. OpenAlex counts 79 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
79
Most cited in
2020 (10)
Field-weighted impact
11.84
References
18
Authors
2

Abstract

We consider the stochastic multi-armed bandit problem with a prior distribution on the reward distributions. We are interested in studying prior-free and prior-dependent regret bounds, very much in the same spirit than the usual distribution-free and distribution-dependent bounds for the non-Bayesian stochastic bandit. We first show that Thompson Sampling attains an optimal prior-free bound in the sense that for any prior distribution its Bayesian regret is bounded from above by 14√nK. This result is unimprovable in the sense that there exists a prior distribution such that any algorithm has a Bayesian regret bounded from below by 1 over 20√nK. We also study the case of priors for the setting of Bubeck et al. [2013] (where the optimal mean is known as well as a lower bound on the smallest gap) and we show that in this case the regret of Thompson Sampling is in fact uniformly bounded over time, thus showing that Thompson Sampling can greatly take advantage of the nice properties of these priors.

Cite this paper

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

APA 7

Bubeck, S., & Liu, C.-Y. (2014). Prior-free and prior-dependent regret bounds for Thompson Sampling. Conference on Information Sciences and Systems, 26, 1–9. https://doi.org/10.1109/ciss.2014.6814158

MLA 9

Bubeck, Sébastien, and Che-Yu Liu. “Prior-free and prior-dependent regret bounds for Thompson Sampling.” Conference on Information Sciences and Systems, vol. 26, 2014, pp. 1–9. https://doi.org/10.1109/ciss.2014.6814158.

Chicago

Bubeck, Sébastien and Che-Yu Liu. 2014. “Prior-free and prior-dependent regret bounds for Thompson Sampling.” Conference on Information Sciences and Systems 26: 1–9. https://doi.org/10.1109/ciss.2014.6814158.

Harvard

Bubeck, S. and Liu, C.-Y. (2014) ‘Prior-free and prior-dependent regret bounds for Thompson Sampling’, Conference on Information Sciences and Systems, 26, pp. 1–9. doi:10.1109/ciss.2014.6814158.

IEEE

S. Bubeck and C.-Y. Liu, “Prior-free and prior-dependent regret bounds for Thompson Sampling,” Conference on Information Sciences and Systems, vol. 26, pp. 1–9, 2014, doi: 10.1109/ciss.2014.6814158.

BibTeX

@inproceedings{bubeck2014prior,
  title     = {{Prior-free and prior-dependent regret bounds for Thompson Sampling}},
  author    = {Bubeck, Sébastien and Liu, Che-Yu},
  booktitle = {Conference on Information Sciences and Systems},
  year      = {2014},
  volume    = {26},
  pages     = {1--9},
  doi       = {10.1109/ciss.2014.6814158},
  url       = {https://doi.org/10.1109/ciss.2014.6814158}
}

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

Citations by year

YearCitationsShare of the best year
201633
201755
201888
201955
20201010
20211010
202244
202377
202477
202511

Its field-weighted citation impact is 11.84: it has been cited 11.84 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • Thompson sampling
  • stochastic bandits
  • Bayesian regret
  • regret lower bounds

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?

Bubeck, S., & Liu, C.-Y. (2014). Prior-free and prior-dependent regret bounds for Thompson Sampling. Conference on Information Sciences and Systems, 26, 1–9. https://doi.org/10.1109/ciss.2014.6814158

How many times has this paper been cited?

79 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?

Sébastien Bubeck, Che-Yu Liu.

What is the DOI of this paper?

10.1109/ciss.2014.6814158, permanently at https://doi.org/10.1109/ciss.2014.6814158. 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.