Conference paper · 2022 · Open access

Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits

Tianyuan Jin, Pan Xu, Xiaokui Xiao, Animashree Anandkumar

neural information processing systems, 38475–38487 · Published 1 January 2022 · DOI 10.52202/068431-2788

Open PDFView at the publisherCite this paper

In brief

“Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits” is a 2022 conference paper by Tianyuan Jin and 3 co-authors, published in neural information processing systems. OpenAlex counts 24 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
24
Most cited in
2024 (9)
Field-weighted impact
5.16
References
21
Authors
4

Abstract

We study the regret of Thompson sampling (TS) algorithms for exponential family bandits, where the reward distribution is from a one-dimensional exponential family, which covers many common reward distributions including Bernoulli, Gaussian, Gamma, Exponential, etc. We propose a Thompson sampling algorithm, termed ExpTS, which uses a novel sampling distribution to avoid the under-estimation of the optimal arm. We provide a tight regret analysis for ExpTS, which simultaneously yields both the finite-time regret bound as well as the asymptotic regret bound. In particular, for a $K$-armed bandit with exponential family rewards, ExpTS over a horizon $T$ is sub-UCB (a strong criterion for the finite-time regret that is problem-dependent), minimax optimal up to a factor $\sqrt{\log K}$, and asymptotically optimal, for exponential family rewards. Moreover, we propose ExpTS$^+$, by adding a greedy exploitation step in addition to the sampling distribution used in ExpTS, to avoid the over-estimation of sub-optimal arms. ExpTS$^+$ is an anytime bandit algorithm and achieves the minimax optimality and asymptotic optimality simultaneously for exponential family reward distributions. Our proof techniques are general and conceptually simple and can be easily applied to analyze standard Thompson sampling with specific reward distributions.

Cite this paper

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

APA 7

Jin, T., Xu, P., Xiao, X., & Anandkumar, A. (2022). Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits. neural information processing systems, 38475–38487. https://doi.org/10.52202/068431-2788

MLA 9

Jin, Tianyuan, et al. “Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits.” neural information processing systems, 2022, pp. 38475–38487. https://doi.org/10.52202/068431-2788.

Chicago

Jin, Tianyuan, Pan Xu, Xiaokui Xiao, and Animashree Anandkumar. 2022. “Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits.” neural information processing systems: 38475–38487. https://doi.org/10.52202/068431-2788.

Harvard

Jin, T. et al. (2022) ‘Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits’, neural information processing systems, pp. 38475–38487. doi:10.52202/068431-2788.

IEEE

T. Jin, P. Xu, X. Xiao, and A. Anandkumar, “Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits,” neural information processing systems, pp. 38475–38487, 2022, doi: 10.52202/068431-2788.

BibTeX

@inproceedings{jin2022finite,
  title     = {{Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits}},
  author    = {Jin, Tianyuan and Xu, Pan and Xiao, Xiaokui and Anandkumar, Animashree},
  booktitle = {neural information processing systems},
  year      = {2022},
  pages     = {38475--38487},
  doi       = {10.52202/068431-2788},
  url       = {https://doi.org/10.52202/068431-2788}
}

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

Citations by year

YearCitationsShare of the best year
202111
202344
202499
202555
202655

Its field-weighted citation impact is 5.16: it has been cited 5.16 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
  • multi-armed bandits
  • minimax optimality

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?

Jin, T., Xu, P., Xiao, X., & Anandkumar, A. (2022). Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits. neural information processing systems, 38475–38487. https://doi.org/10.52202/068431-2788

How many times has this paper been cited?

24 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?

Tianyuan Jin, Pan Xu, Xiaokui Xiao, Animashree Anandkumar.

What is the DOI of this paper?

10.52202/068431-2788, permanently at https://doi.org/10.52202/068431-2788. 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.