lil'HDoC:一种小阈值间隙下的优质臂识别算法
lil'HDoC: An Algorithm for Good Arm Identification under Small Threshold Gap
AI总结:
针对小阈值间隙下的优质臂识别老虎机问题,提出lil'HDoC算法以降低HDoC的样本复杂度,理论与实验均验证其性能优于现有最优算法。
摘要:
优质臂识别(Good Arm Identification,GAI)是一类纯探索式老虎机问题,在该问题中,单个学习器一旦识别出某条臂为优质臂,就会立即输出该臂。优质臂的定义是期望奖励大于或等于给定阈值的臂。本文聚焦于小阈值间隙下的GAI问题,阈值间隙指的是各臂的期望奖励与给定阈值之间的距离。我们提出了一种名为lil'HDoC的新算法,可显著降低HDoC算法的总样本复杂度。我们证明,当期望奖励与阈值的距离较小时,lil'HDoC中前λ个输出臂的样本复杂度,除了一个可忽略的项之外,均受原始HDoC算法的样本复杂度约束。大量实验证实,我们的算法在合成数据集和真实世界数据集上的表现均优于当前最优算法。
英文摘要:
Good arm identification (GAI) is a pure-exploration bandit problem in which a single learner outputs an arm as soon as it is identified as a good arm. A good arm is defined as an arm with an expected reward greater than or equal to a given threshold. This paper focuses on the GAI problem under a small threshold gap, which refers to the distance between the expected rewards of arms and the given threshold. We propose a new algorithm called lil'HDoC to significantly improve the total sample complexity of the HDoC algorithm. We demonstrate that the sample complexity of the first $λ$ output arm in lil'HDoC is bounded by the original HDoC algorithm, except for one negligible term, when the distance between the expected reward and threshold is small. Extensive experiments confirm that our algorithm outperforms the state-of-the-art algorithms in both synthetic and real-world datasets.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。