Papers › On the Suboptimality of Thompson Sampling in High Dimensions

On the Suboptimality of Thompson Sampling in High Dimensions

10 Feb 2021NeurIPS 2021 12arXiv:2102.05502archive 2025-07-28

Raymond Zhang, Richard Combes

In this paper we consider Thompson Sampling (TS) for combinatorial semi-bandits. We demonstrate that, perhaps surprisingly, TS is sub-optimal for this problem in the sense that its regret scales exponentially in the ambient dimension, and its minimax regret scales almost linearly. This phenomenon occurs under a wide variety of assumptions including both non-linear and linear reward functions, with Bernoulli distributed rewards and uniform priors. We also show that including a fixed amount of forced exploration to TS does not alleviate the problem. We complement our theoretical results with numerical results and show that in practice TS indeed can perform very poorly in some high dimensional situations.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Thompson SamplingVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

TS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections