arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.03586cs.LGstat.ML
收藏

利用插值模型与误差界实现可验证的科学机器学习

Leveraging Interpolation Models and Error Bounds for Verifiable Scientific Machine Learning

Argonne National Laboratory(阿贡国家实验室);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);The Pennsylvania State University(宾夕法尼亚州立大学)

Tyler Chang, Andrew Gillette, Romit Maulik

AI总结:

本文提出一种可验证科学机器学习方法,证明标准插值误差界可高效计算、插值方法间比较有助于验证,并能在深度学习潜在空间上增强黑盒可解释性,以翼型升阻比预测为例验证。

摘要:

为现代科学机器学习工作流设计有效的验证与确认技术颇具挑战。统计方法数量众多且易于部署,但往往依赖于对相关数据和方法的主观假设。经典插值技术的误差界能够提供数学上严格的精度估计,但在计算上通常难以或无法实际确定。本文提出了一种兼顾两者的可验证科学机器学习方法,并证明:(1) 多种标准插值技术具有信息丰富的误差界,且这些误差界可以被高效计算或估计;(2) 不同插值方法之间的性能比较有助于实现验证目标;(3) 在深度学习技术生成的潜在空间上部署插值方法,能够为黑盒模型提供一定的可解释性。我们以从翼型图像预测升阻比为例,对该方法进行了详细的案例研究。本工作开发的代码已公开于 Github 代码库。

英文摘要:

Effective verification and validation techniques for modern scientific machine learning workflows are challenging to devise. Statistical methods are abundant and easily deployed, but often rely on speculative assumptions about the data and methods involved. Error bounds for classical interpolation techniques can provide mathematically rigorous estimates of accuracy, but often are difficult or impractical to determine computationally. In this work, we present a best-of-both-worlds approach to verifiable scientific machine learning by demonstrating that (1) multiple standard interpolation techniques have informative error bounds that can be computed or estimated efficiently; (2) comparative performance among distinct interpolants can aid in validation goals; (3) deploying interpolation methods on latent spaces generated by deep learning techniques enables some interpretability for black-box models. We present a detailed case study of our approach for predicting lift-drag ratios from airfoil images. Code developed for this work is available in a public Github repository.

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。

↑