数学
度量(数据仓库)
因子(编程语言)
实验设计
领域(数学分析)
算法
过程(计算)
贝叶斯概率
高斯分布
优化设计
计算机实验
高斯过程
数学优化
数据挖掘
统计
计算机科学
数学分析
物理
量子力学
程序设计语言
操作系统
作者
Yao Xiao,Shiqi Wang,Hong Qin,Jianhui Ning
出处
期刊:Statistics
[Informa]
日期:2023-04-27
卷期号:57 (3): 534-553
被引量:2
标识
DOI:10.1080/02331888.2023.2204438
摘要
Uniform designs seek to distribute design points uniformly in the experimental domain. Some discrepancies have been developed to measure the uniformity by treating all factors equally. It is reasonable when there exists no prior information about the system or when the potential model is completely unclear. However, in the situation of sequential designs, experimental information, such as the importance of each factor, would be obtained from previous stage experiments. With this fact, the weighted L2-discrepancy is more suitable than the original discrepancy for choosing follow-up designs. In this paper, the sequentially weighted uniform design is proposed, which is obtained by minimizing the weighted L2-discrepancy. The weights, indicating the relative importance of each factor, are estimated through a Bayesian hierarchical Gaussian process method based on serial experimental data. Results from several classic computer simulator examples, as well as a real application in circuit design, demonstrate that the performance of our new method surpasses that of its counterparts.
科研通智能强力驱动
Strongly Powered by AbleSci AI