Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification

arXiv:2202.05193v3 Announce Type: replace-cross
Abstract: We consider the fixed-budget best arm identification problem with rewards following normal distributions. In this problem, the forecaster is given $K$ arms (or treatments) and $T$ time steps. The forecaster attempts to find the arm with the largest mean, via an adaptive experiment conducted using an algorithm. The algorithm's performance is evaluated by simple regret, reflecting the quality of the estimated best arm. While frequentist simple regret can decrease exponentially with respect to $T$, Bayesian …

abstract algorithm arm arxiv bayes budget cs.lg experiment identification math.pr mean normal performance stat.ml type via