An induced natural selection heuristic for finding optimal Bayesian experimental designs

An induced natural selection heuristic for finding optimal Bayesian experimental designs
复制标题

用于寻找最佳贝叶斯实验设计的诱导自然选择启发式

DOI:
10.1016/j.csda.2018.04.011
复制
发表时间:
2018
影响因子:
1.8
通讯作者:
Price D
Price D
中科院分区:
数学3区
文献类型:
--
作者:
Price D

文献摘要

参考文献

被引文献

相似文献

贝叶斯最优试验设计具有巨大的潜力,可以为收集数据提供信息,从而增强我们对各种过程的理解。然而,一个主要的障碍是难以评估具有大的或高维的设计空间的问题的最佳设计。针对最优贝叶斯试验设计问题,提出了一种适用于一般优化问题的高效搜索启发式算法。启发式算法在初始的、随机生成的一组输入值上对目标(效用)函数求值。在算法的每一代,如果输入值的相应目标(效用)函数满足某些接受标准,则输入值被“接受”,并且关于这些接受点对新的输入进行采样。通过对先前考虑的死亡、药代动力学和Logistic回归模型的最优贝叶斯试验设计进行评估,证明了新算法的有效性。与目前的“黄金标准”方法的比较表明,该算法对于中等规模(约40维)的设计问题是一种计算效率较高的替代方法。
Bayesian optimal experimental design has immense potential to inform the collection of data so as to subsequently enhance our understanding of a variety of processes. However, a major impediment is the difficulty in evaluating optimal designs for problems with large, or high-dimensional, design spaces. An efficient search heuristic suitable for general optimisation problems, with a particular focus on optimal Bayesian experimental design problems, is proposed. The heuristic evaluates the objective (utility) function at an initial, randomly generated set of input values. At each generation of the algorithm, input values are “accepted” if their corresponding objective (utility) function satisfies some acceptance criteria, and new inputs are sampled about these accepted points. The new algorithm is demonstrated by evaluating the optimal Bayesian experimental designs for the previously considered death, pharmacokinetic and logistic regression models. Comparisons to the current “gold-standard” method are given to demonstrate the proposed algorithm as a computationally-efficient alternative for moderately-large design problems (i.e., up to approximately 40-dimensions).
用于导出群体药代动力学研究的采样时间和窗口的连续蒙特卡罗方法
DOI: --
发表时间: 2012
影响因子: 2.5
作者:
James McGree;C. Drovandi;A. Pettitt
通讯作者: A. Pettitt
DOI: --
发表时间: 2007
期刊: Online World Conference on Soft Computing in Industrial Applications
影响因子: --
作者:
Gareth E. Evans;J. Keith;Dirk P. Kroese
通讯作者: Dirk P. Kroese
DOI: 10.1080/10543406.2010.500065
发表时间: 2012-01-01
影响因子: 1.1
作者:
Duffull, Stephen B.;Graham, Gordon;Eccleston, John
通讯作者: Eccleston, John
DOI: 10.3390/e17031063
发表时间: 2015-03-01
期刊: ENTROPY
影响因子: 2.7
作者:
Ryan, Elizabeth G.;Drovandi, Christopher C.;Pettitt, Anthony N.
通讯作者: Pettitt, Anthony N.
使用 ABC 有效确定最佳贝叶斯实验设计:流行病最佳观察的案例研究
DOI: --
发表时间: 2016
期刊:
影响因子: --
作者:
David J. Price;N. Bean;J. Ross;J. Tuke
通讯作者: J. Tuke