发表机构
Université Paris-Saclay, AgroParisTech, INRAE; INSA Lyon, CNRS, École Centrale Lyon, Université Claude Bernard Lyon 1; EDF R&D PRISME（巴黎萨克雷大学, 农业巴黎技术学院, 法国国家农业食品环境研究院; 里昂国立应用科学学院, 法国国家科学研究中心, 里昂中央理工学院, 里昂第一大学; 法国电力集团研发PRISME）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种贝叶斯混合模型方法，通过比较纯代码模型与差异校正模型，利用混合权重后验分布及阈值化分配规则，实现计算机代码的全局与局部验证。
AI 中文摘要
当计算机代码对复杂物理系统进行建模时，仅进行校准是不够的；还必须评估是否需要引入差异项。本文通过贝叶斯混合方法研究计算机代码验证，该方法将纯代码模型与经差异校正的模型进行比较。该方法依赖于混合权重的后验分布，该权重衡量两个竞争分布的相对支持程度。在假设代码关于校准参数是线性的，或者能够被线性代理模型很好地近似的前提下，我们表明，即使对某些公共参数赋予无信息先验，混合分量共享参数也可用于结合灵活建模。推断通过Metropolis-within-Gibbs算法执行。此外，我们引入了一种阈值化分配规则，该规则通过提供局部诊断来补充全局混合权重，以确定沿输入域哪些位置确实需要差异校正分量。除了全局模型比较之外，所提出的方法还能够通过识别沿输入域哪些位置确实需要差异校正分量来进行局部模型判别。
英文摘要
When computer codes model complex physical systems, calibration alone is insufficient; one must also assess whether a discrepancy term is needed. In this paper, we study computer code validation through a Bayesian mixture approach that compares a pure-code model with a discrepancy-corrected model. The method relies on the posterior distribution of a mixture weight, which measures the relative support of the two competing distributions. Under the assumption that the code is linear in the calibration parameters, or can be well approximated by a linear surrogate, we show that mixture component-shared parameters can be used to combine flexible modeling, even when noninformative priors are assigned to some common parameters. Inference is performed using a Metropolis-within-Gibbs algorithm. In addition, we introduce a thresholded allocation rule that complements the global mixture weight by providing a local diagnostic of where the discrepancy-corrected component is truly needed along the input domain. Beyond global model comparison, the proposed approach is also able to perform local model discrimination by identifying where the discrepancy-corrected component is truly needed along the input domain.
