Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
Proceedings of the 31st International Conference on Algorithmic Learning Theory, PMLR 117:862-889, 2020.
Stochastic Rank-One Bandits are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but do not match the existing lower bound for this problem. We close this gap by first proving that rank-one bandits are a particular instance of unimodal bandits, and then providing a new analysis of Unimodal Thompson Sampling (UTS). We prove an asymptotically optimal regret bound on the frequentist regret of UTS and we support our claims with simulations showing the significant improvement of our method compared to the state-of-the-art.