arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.14722stat.MLcs.LGmath.OC
收藏

最优计算预算分配算法的收敛速度分析

Convergence Rate Analysis for Optimal Computing Budget Allocation Algorithms

Nanyang Technological University(南洋理工大学);City University of Hong Kong(香港城市大学)

Yanwen Li, Siyang Gao

摘要:

序优化(OO)是一种广泛研究的离散事件动态系统(DEDS)优化技术。它通过抽样在有限集合中评价系统设计的性能,目的是正确地进行设计的顺序比较。在OO中一个著名的方法是最优计算预算分配(OCBA)。它建立了分配给每个设计的样本数的最优性条件,并且满足最优性条件的样本分配显示出渐近最大化最佳设计的正确选择概率。在本文中,我们研究了两个流行的OCBA算法。每个设计的样本的方差已知,我们表征其收敛速度相对于不同的性能指标。我们首先证明了这两个OCBA算法在正确选择概率和期望机会成本的度量下达到了最优收敛速度。它填补了OCBA算法收敛性分析的空白。接下来,我们将我们的分析扩展到累积遗憾的度量,这是机器学习领域研究的主要度量。我们证明了在累积遗憾的情况下,两个OCBA算法只需稍加修改就能达到最优收敛速度。它表明了更广泛使用的OCBA最优性条件的基础上设计的算法的潜力。

英文摘要:

Ordinal optimization (OO) is a widely-studied technique for optimizing discrete-event dynamic systems (DEDS). It evaluates the performance of the system designs in a finite set by sampling and aims to correctly make ordinal comparison of the designs. A well-known method in OO is the optimal computing budget allocation (OCBA). It builds the optimality conditions for the number of samples allocated to each design, and the sample allocation that satisfies the optimality conditions is shown to asymptotically maximize the probability of correct selection for the best design. In this paper, we investigate two popular OCBA algorithms. With known variances for samples of each design, we characterize their convergence rates with respect to different performance measures. We first demonstrate that the two OCBA algorithms achieve the optimal convergence rate under measures of probability of correct selection and expected opportunity cost. It fills the void of convergence analysis for OCBA algorithms. Next, we extend our analysis to the measure of cumulative regret, a main measure studied in the field of machine learning. We show that with minor modification, the two OCBA algorithms can reach the optimal convergence rate under cumulative regret. It indicates the potential of broader use of algorithms designed based on the OCBA optimality conditions.

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。

↑