Conference paper · 2024 · Open access

Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox

Raymond J. Zhang, Richard Combes

neural information processing systems, 89437–89467 · Published 1 January 2024 · DOI 10.52202/079017-2839

Open PDFView at the publisherCite this paper

In brief

“Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox” is a 2024 conference paper by Raymond J. Zhang and Richard Combes, published in neural information processing systems. OpenAlex counts 3 citations as of 19 November 2026, which puts it in the top 4% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
3
Most cited in
2026 (3)
Field-weighted impact
1.07
References
14
Authors
2

Abstract

We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the "mismatched sampling paradox": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatched-Paradox

Cite this paper

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

APA 7

Zhang, R. J., & Combes, R. (2024). Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox. neural information processing systems, 89437–89467. https://doi.org/10.52202/079017-2839

MLA 9

Zhang, Raymond J., and Richard Combes. “Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox.” neural information processing systems, 2024, pp. 89437–89467. https://doi.org/10.52202/079017-2839.

Chicago

Zhang, Raymond J. and Richard Combes. 2024. “Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox.” neural information processing systems: 89437–89467. https://doi.org/10.52202/079017-2839.

Harvard

Zhang, R. J. and Combes, R. (2024) ‘Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox’, neural information processing systems, pp. 89437–89467. doi:10.52202/079017-2839.

IEEE

R. J. Zhang and R. Combes, “Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox,” neural information processing systems, pp. 89437–89467, 2024, doi: 10.52202/079017-2839.

BibTeX

@inproceedings{zhang2024thompson,
  title     = {{Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox}},
  author    = {Zhang, Raymond J. and Combes, Richard},
  booktitle = {neural information processing systems},
  year      = {2024},
  pages     = {89437--89467},
  doi       = {10.52202/079017-2839},
  url       = {https://doi.org/10.52202/079017-2839}
}

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
  • combinatorial bandits
  • linear bandits
  • regret analysis
  • 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?

Zhang, R. J., & Combes, R. (2024). Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox. neural information processing systems, 89437–89467. https://doi.org/10.52202/079017-2839

How many times has this paper been cited?

3 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?

Raymond J. Zhang, Richard Combes.

What is the DOI of this paper?

10.52202/079017-2839, permanently at https://doi.org/10.52202/079017-2839. 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.