The Influence of Shape Constraints on the Thresholding Bandit Problem

We investigate the stochastic Thresholding Bandit problem (TBP) under several shape constraints. On top of (i) the vanilla, unstructured TBP, we consider the case where (ii) the sequence of arm's means is monotonically increasing MTBP, (iii) the case where is unimodal UTBP and (iv) the case where is concave CTBP. In the TBP problem the aim is to output, at the end of the sequential game, the set of arms whose means are above a given threshold. The regret is the highest gap between a misclassified arm and the threshold. In the fixed budget setting, we provide problem independent minimax rates for the expected regret in all settings, as well as associated algorithms. We prove that the minimax rates for the regret are (i) for TBP, (ii) for MTBP, (iii) for UTBP and (iv) for CTBP, where is the number of arms and is the budget. These rates demonstrate that the dependence on of the minimax regret varies significantly depending on the shape constraint. This highlights the fact that the shape constraints modify fundamentally the nature of the TBP.
View on arXiv