A Note on Bounding Regret of the CUCB Contextual Combinatorial Bandit
arXiv:1902.07500
Abstract
We revisit the proof by Qin et al. (2014) of bounded regret of the CUCB contextual combinatorial bandit. We demonstrate an error in the proof of volumetric expansion of the moment matrix, used in upper bounding a function of context vector norms. We prove a relaxed inequality that yields the originally-stated regret bound.
3 pages