Author name: Yan Shuo Tan, Kenyon Ng, Ruizhe Deng, Sumetha Loganathan, Qiong Zhang, Bibhas Chakraborty

arXiv:2605.10137v1 Announce Type: new
Abstract: Thompson sampling is a widely used strategy for contextual bandits: at each round, it samples a reward function from a Bayesian posterior and acts greedily under that sample. Prior-data fitted networks (…