Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2510.10730v3 Announce Type: replace-cross Abstract: We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Model Ensemble Sampling…

devscience

Sources

• T1Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual BanditsarXiv24 Sept, 04:00