Bayesian Nonparametric Thompson Sampling for Multi-Armed Bandits

arXiv:1808.02932 · stat.ML, cs.LG, stat.CO · Submitted 2018-08-08 · Read on arXiv

stat.ML, cs.LG, stat.CO

Submitted: 2018-08-08

Updated: 2026-10-13

Terminology

• Regret — 5× in this paper · explained in 3 episodes

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier