arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.14723stat.MLcs.LGmath.OC
收藏

近视排序和选择过程的渐近最优性

Asymptotic Optimality of Myopic Ranking and Selection Procedures

Nanyang Technological University(南洋理工大学);City University of Hong Kong(香港城市大学);University of Tennessee-Knoxville(田纳西大学诺克斯维尔分校)

Yanwen Li, Siyang Gao, Zhongshun Shi

摘要:

排序和选择(R&S)是研究离散事件动态系统的一个流行模型。它的目的是从有限集合中选择最佳设计(具有最大平均性能的设计),其中每个设计的平均值是未知的,并且必须通过样本学习。大量的研究工作已经致力于这个问题在文献中开发的程序具有优越的经验性能,并显示其最优性。在这些努力中,近视手术很受欢迎。他们选择最好的设计使用一个“天真”的机制,迭代和近视改善的近似的客观措施。虽然他们是基于简单的数学和缺乏理论支持,他们被证明是非常有效的,往往取得了竞争力的经验表现相比,后来提出的程序,并被证明是渐近最优的。在本文中,我们从理论上分析了这些短视的程序,并证明了他们也满足R&S的最优性条件,就像其他流行的R&S方法。它解释了近视程序在各种数值测试中的良好性能,并提供了对高效R&S程序的结构和理论发展的深入了解。

英文摘要:

Ranking and selection (R&S) is a popular model for studying discrete-event dynamic systems. It aims to select the best design (the design with the largest mean performance) from a finite set, where the mean of each design is unknown and has to be learned by samples. Great research efforts have been devoted to this problem in the literature for developing procedures with superior empirical performance and showing their optimality. In these efforts, myopic procedures were popular. They select the best design using a 'naive' mechanism of iteratively and myopically improving an approximation of the objective measure. Although they are based on simple heuristics and lack theoretical support, they turned out highly effective, and often achieved competitive empirical performance compared to procedures that were proposed later and shown to be asymptotically optimal. In this paper, we theoretically analyze these myopic procedures and prove that they also satisfy the optimality conditions of R&S, just like some other popular R&S methods. It explains the good performance of myopic procedures in various numerical tests, and provides good insight into the structure and theoretical development of efficient R&S procedures.

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。

↑