The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms

arXiv:2002.10121v4 Announce Type: replace
Abstract: We investigate a Bayesian $k$-armed bandit problem in the \emph{many-armed} regime, where $k \geq \sqrt{T}$ and $T$ represents the time horizon. Initially, and aligned with recent literature on many-armed bandit problems, we observe that subsampling plays a key role in designing optimal algorithms; the conventional UCB algorithm is sub-optimal, whereas a subsampled UCB (SS-UCB), which selects $\Theta(\sqrt{T})$ arms for execution under the UCB framework, achieves rate-optimality. However, despite SS-UCB's theoretical promise of optimal regret, it …

abstract algorithms arxiv bayesian cs.lg designing horizon key literature observe role stat.ml type