arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02575math.STstat.TH
收藏

一种面向多保真代理建模的贝叶斯神经网络方法

A Bayesian neural network approach to Multi-fidelity surrogate modelling

Baptiste Kerleguer, Claire Cannamela, Josselin Garnier

AI总结:

本文提出GPBNN方法,将高斯过程回归与贝叶斯神经网络结合,利用低保真输出仿真器辅助高保真建模,并完整量化预测不确定性,用于分层多保真代理建模。

摘要:

本文研究分层多保真背景下计算机代码输出的代理建模问题,即输出可以在不同精度和计算成本水平上进行评估。利用低保真和高保真水平下的输出观测,我们提出了一种将高斯过程(GP)回归与贝叶斯神经网络(BNN)相结合的方法,称为GPBNN。低保真输出被视为单保真代码,使用经典GP回归处理。高保真输出由一个BNN近似,该BNN除高保真观测外,还纳入低保真输出仿真器的精心选择的实现。最终代理模型的预测不确定性随后通过对不同模型的不确定性及其相互作用的完整刻画来量化。GPBNN与大多数允许量化预测不确定性的多保真回归方法进行了比较。

英文摘要:

This paper deals with surrogate modelling of a computer code output in a hierarchical multi-fidelity context, i.e., when the output can be evaluated at different levels of accuracy and computational cost. Using observations of the output at low- and high-fidelity levels, we propose a method that combines Gaussian process (GP) regression and Bayesian neural network (BNN), in a method called GPBNN. The low-fidelity output is treated as a single-fidelity code using classical GP regression. The high-fidelity output is approximated by a BNN that incorporates, in addition to the high-fidelity observations, well-chosen realisations of the low-fidelity output emulator. The predictive uncertainty of the final surrogate model is then quantified by a complete characterisation of the uncertainties of the different models and their interaction. GPBNN is compared with most of the multi-fidelity regression methods allowing to quantify the prediction uncertainty.

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。

↑