Adaptive Design and Analysis of Supercomputer Experiments
Adaptive Design and Analysis of Supercomputer Experiments
复制标题
DOI：
10.1198/tech.2009.0015
复制
发表时间：
2009-05-01
期刊：
影响因子：
2.5
通讯作者：
Lee, Herbert K. H.
中科院分区：
文献类型：
--
作者：
Gramacy, Robert B.;Lee, Herbert K. H.
通常进行计算机实验是为了对物理实验的响应面进行建模，这些物理实验可能过于昂贵或难以运行，除非使用模拟器。在密集的网格上运行实验可能会非常昂贵，而在事先选择的稀疏设计上运行可能会导致部分空间的信息不足，特别是当表面需要非平稳模型时。我们提出了一种自动探索空间的方法，同时拟合响应面，使用预测不确定性来指导后续的实验运行。我们使用新发展的贝叶斯树高斯过程作为代理模型；一个完全的贝叶斯方法允许明确的测量不确定性。我们开发了一个自适应顺序设计框架，通过使用混合方法，将统计文献中的最佳策略与主动学习文献中的灵活策略相结合，来应对异步、随机、基于代理的超级计算环境。该方法的优点在几个例子中得到了证明，包括一个火箭助推器的激励计算流体动力学模拟。
Computer experiments often are performed to allow modeling of a response surface of a physical experiment that can be too costly or difficult to run except by using a simulator. Running the experiment over a dense grid can be prohibitively expensive, yet running over a sparse design chosen in advance can result in insufficient information in parts of the space, particularly when the surface calls for a nonstationary model. We propose an approach that automatically explores the space while simultaneously fitting the response surface, using predictive uncertainty to guide subsequent experimental runs. We use the newly developed Bayesian treed Gaussian process as the surrogate model; a fully Bayesian approach allows explicit measures of uncertainty. We develop an adaptive sequential design framework to cope with an asynchronous, random, agent-based supercomputing environment by using a hybrid approach that melds optimal strategies from the statistics literature with flexible strategies from the active learning literature. The merits of this approach are borne out in several examples, including the motivating computational fluid dynamics simulation of a rocket booster.