Optimal experimental design for prediction based on push-forward probability measures

Optimal experimental design for prediction based on push-forward probability measures
复制标题

基于前推概率测度的预测优化实验设计

DOI:
10.1016/j.jcp.2020.109518
复制
发表时间:
2020
影响因子:
4.1
通讯作者:
Wildey, T.
Wildey, T.
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Butler, T.;Jakeman, J.D.;Wildey, T.

文献摘要

参考文献

被引文献

相似文献

验证实验数据对于提高仿真辅助决策和设计的可信度至关重要。本文提出了一种方法,它使用一个计算模型来指导实验数据的最佳采集,以产生感兴趣的数量(QoI)的数据知情的预测。许多最优实验设计(OED)策略选择能够最大化某些效用的数据,这些效用衡量不确定模型参数的不确定性的减少,例如这些参数的先验分布和后验分布之间的预期信息增益。在本文中,我们试图通过参数预测映射最大化从初始(先验)密度的推进到更新(后验)密度的推进所获得的预期信息。提出的配方是基于一个特定的一类随机逆问题的解决方案,寻求一个概率密度,这是一致的模型和数据的意义上说,这个密度的推进通过参数可观察的地图匹配的目标密度的可观察的数据。虽然这个随机逆问题构成了我们方法的数学基础,但我们开发了一个一步算法,专注于推进概率测度,利用预测推理来绕过构建随机逆问题的解决方案。大量的数值结果表明,该最佳实验设计的预测和方便比较,我们的方法与传统的OED的效用。
Incorporating experimental data is essential for increasing the credibility of simulation-aided decision making and design. This paper presents a method which uses a computational model to guide the optimal acquisition of experimental data to produce data-informed predictions of quantities of interest (QoI). Many strategies for optimal experimental design (OED) select data that maximize some utility that measures the reduction in uncertainty of uncertain model parameters, for example the expected information gain between prior and posterior distributions of these parameters. In this paper, we seek to maximize the expected information gained from the push-forward of an initial (prior) density to the push-forward of the updated (posterior) density through the parameter-to-prediction map. The formulation presented is based upon the solution of a specific class of stochastic inverse problems which seeks a probability density that is consistent with the model and the data in the sense that the push-forward of this density through the parameter-to-observable map matches a target density on the observable data. While this stochastic inverse problem forms the mathematical basis for our approach, we develop a one-step algorithm, focused on push-forward probability measures, that leverages inference-for-prediction to bypass constructing the solution to the stochastic inverse problem. A number of numerical results are presented to demonstrate the utility of thisoptimal experimental design for predictionand facilitate comparison of our approach with traditional OED.
贝叶斯自适应探索
DOI: 10.1063/1.1751377
发表时间: 2004
期刊: arXiv: Astrophysics
影响因子: --
作者:
T. Loredo
通讯作者: T. Loredo
使用响应方差准则的基于仿真的优化设计
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
A. Solonen;H. Haario;M. Laine
通讯作者: M. Laine
大规模非线性离散不适定反问题设计的数值方法
DOI: 10.1088/0266-5611/26/2/025002
发表时间: 2010
期刊: Inverse Problems
影响因子: 2.1
作者:
E. Haber;L. Horesh
通讯作者: L. Horesh
DOI: --
发表时间: 2017
期刊:
影响因子: --
作者:
T. Butler;J. Jakeman;T. Wildey
通讯作者: T. Wildey
DOI: 10.1088/1361-6420/aad210
发表时间: 2018-09-01
期刊: INVERSE PROBLEMS
影响因子: 2.1
作者:
Attia, Ahmed;Alexanderian, Alen;Saibaba, Arvind K.
通讯作者: Saibaba, Arvind K.