First-order Bayesian regret analysis of Thompson sampling

MaRDI QIDQ7025144zbMATH OpenFDO

Authors Sébastien Bubeck, Mark Sellke

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/bubeck20a.html

zbMATH Keywords

multi-armed banditThompson sampling

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• An information-theoretic analysis of Thompson sampling
• Feedback graph regret bounds for Thompson sampling and UCB
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
• On tail probabilities for martingales
• On the likelihood that one unkrown probability exeeds another in view of the evidence of two samples.
• Regret in online combinatorial optimization
• The Nonstochastic Multiarmed Bandit Problem

This page was built for publication: First-order Bayesian regret analysis of Thompson sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025144)