Thompson sampling for adversarial bit prediction

MaRDI QIDQ7025126zbMATH OpenFDO

Authors Yuval Lewi, Haim Kaplan, Yishay Mansour

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/lewi20a.html

zbMATH Keywords

regretmulti-armed banditsThompson samplingadversarial settingbit prediction

Mathematics Subject Classification ID

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

Cites work

• 10.1162/1532443041827952
• A Tutorial on Thompson Sampling
• An information-theoretic analysis of Thompson sampling
• Asymptotic minimax regret for data compression, gambling, and prediction
• Efficient algorithms for online decision problems
• Finite-time analysis of the multiarmed bandit problem
• Introduction to multi-armed bandits
• Near-optimal regret bounds for Thompson sampling
• On prediction of individual sequences
• On the likelihood that one unkrown probability exeeds another in view of the evidence of two samples.
• Prediction, Learning, and Games
• Probability Inequalities for Sums of Bounded Random Variables
• Probability and Computing
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• The Nonstochastic Multiarmed Bandit Problem
• Thompson sampling: an asymptotically optimal finite-time analysis
• Towards optimal algorithms for prediction with expert advice
• Universal prediction
• Universal prediction of individual sequences

This page was built for publication: Thompson sampling for adversarial bit prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025126)