arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.09883math.STstat.TH
收藏

灵敏度分析与广义混沌展开。Sobol指标的下界

Sensitivity Analysis and Generalized Chaos Expansions. Lower Bounds for Sobol indices

O Roustant, F. Gamboa, B Iooss

摘要:

所谓的多项式混沌展开在计算机实验中有着广泛的应用。例如,它是估计Sobol敏感性指数的有力工具。本文考虑了建立在广义张量Hilbert基上的广义混沌展开式。在此框架下,我们重新计算的Sobol'指数,并给出一般的下界,这些指标。与庞加莱{é}微分算子相关联的本征函数系统的情况导致涉及所分析的函数的导数的下界,并且提供了变量筛选的有效工具。这些下界在玩具和现实生活中的模型都证明了它们的准确性。

英文摘要:

The so-called polynomial chaos expansion is widely used in computer experiments. For example, it is a powerful tool to estimate Sobol' sensitivity indices. In this paper, we consider generalized chaos expansions built on general tensor Hilbert basis. In this frame, we revisit the computation of the Sobol' indices and give general lower bounds for these indices. The case of the eigenfunctions system associated with a Poincar{é} differential operator leads to lower bounds involving the derivatives of the analyzed function and provides an efficient tool for variable screening. These lower bounds are put in action both on toy and real life models demonstrating their accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑