无性能退化的批处理顺序减半算法
A Batch Sequential Halving Algorithm without Performance Degradation
AI总结:
本文研究多臂老虎机纯探索中固定大小批次拉臂的性能退化问题,提出SH算法的批处理版本,并通过理论和实验证明其在实际条件下不降低原始算法性能。
摘要:
本文研究多臂老虎机纯探索问题,重点关注以固定大小批次拉臂的场景。批处理已被证明能提升计算效率,但由于反馈延迟和适应性降低,可能导致性能相比原始顺序算法退化。我们引入了Sequential Halving (SH)算法(Karnin et al., 2013)的简单批处理版本,并提供了理论证据,证明在实际条件下批处理不会导致原始算法性能退化。此外,我们通过实验验证了该主张,证明了SH算法在固定大小批次设置中的鲁棒性。
英文摘要:
In this paper, we investigate the problem of pure exploration in the context of multi-armed bandits, with a specific focus on scenarios where arms are pulled in fixed-size batches. Batching has been shown to enhance computational efficiency, but it can potentially lead to a degradation compared to the original sequential algorithm's performance due to delayed feedback and reduced adaptability. We introduce a simple batch version of the Sequential Halving (SH) algorithm (Karnin et al., 2013) and provide theoretical evidence that batching does not degrade the performance of the original algorithm under practical conditions. Furthermore, we empirically validate our claim through experiments, demonstrating the robust nature of the SH algorithm in fixed-size batch settings.
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。