Bayesian Simulation Optimization with Common Random Numbers
Bayesian Simulation Optimization with Common Random Numbers
复制标题
常见随机数的贝叶斯模拟优化
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
J. Branke
中科院分区：
文献类型：
--
作者：
Michael Pearce;Matthias Poloczek;J. Branke
研究了数值搜索域上具有公共随机数的随机模拟优化问题。我们提出了常见随机数的知识梯度（KG-CRN）顺序采样算法，这是对知识梯度的一个简单优雅的修改，它将相关噪声的使用与高斯过程元模型结合在一起。我们将此方法与标准知识梯度和最近提出的允许成对采样的变化进行比较。在相同的实验室条件下，我们的方法显着优于两个基线，同时大大降低了计算成本相比，成对抽样。
We consider the problem of stochastic simulation optimization with common random numbers over a numerical search domain. We propose the Knowledge Gradient for Common Random Numbers (KG-CRN) sequential sampling algorithm, a simple elegant modification to the Knowledge Gradient that incorporates the use of correlated noise in simulation outputs with Gaussian Process meta-models. We compare this method against the standard Knowledge Gradient and a more recently proposed variation that allows for pairwise sampling. Our method significantly outperforms both baselines under identical laboratory conditions while greatly reducing computational cost compared to pairwise sampling.