In this paper, we study sequential testing problems with \emph{overlapping} hypotheses. We first focus on the simple problem of assessing if the mean $\mu$ of a Gaussian distribution is smaller or larger than a fixed $\epsilon>0$; if $\mu\in(-\epsilon,\epsilon)$, both answers are considered to be correct. Then, we consider PAC-best arm identification in a bandit model: given $K$ probability distributions on $\mathbb{R}$ with means $\mu_1,\dots,\mu_K$, we derive the asymptotic complexity of identifying, with risk at most $\delta$, an index $I\in\{1,\dots,K\}$ such that $\mu_I\geq \max_i\mu_i -\epsilon$. We provide non-asymptotic bounds on the error of a parallel General Likelihood Ratio Test, which can also be used for more general testing problems. We further propose lower bound on the number of observation needed to identify a correct hypothesis. Those lower bounds rely on information-theoretic arguments, and specifically on two versions of a change of measure lemma (a high-level form, and a low-level form) whose relative merits are discussed.
翻译:在本文中, 我们研究与 emph{ 重叠] 假设的顺序测试问题。 我们首先关注一个简单的问题, 即评估高山分配的平均值$mu$是否小于或大于固定的$epsilon>0美元; 如果$mu\in( epsilon,\ epsilon) $, 两者的答案都被认为是正确的。 然后, 我们考虑在土匪模式中采用PAC- 最佳手臂识别方式: 在$\mathbb{ R} 美元上给出美元概率分布, 以 $mus_ 1,\ dots,\ mu_ K$, 我们首先关注一个简单的问题, 以美元计风险最多为$\ delta$%1,\ dots, 美元, 以美元计为单位, 这两种答案都被认为是正确的 。 我们进一步提出一个低调的数值, 用于更普通的通用比值比值测试的误差值测试。 我们进一步提出一个更下限的参数, 用于更低的模型的模型的精确度参数, 以两种不同的模型的数值为正确的参数。