arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.26121stat.MLcs.LG
收藏

基于物理信息的机器学习的不确定性诊断

Uncertainty-Aware Diagnostics for Physics-Informed Machine Learning

Massachusetts Institute of Technology(麻省理工学院);University of Melbourne(墨尔本大学);University of California at Berkeley(加州大学伯克利分校)

Mara Daniels, Liam Hodgkinson, Michael Mahoney

摘要:

物理信息机器学习(PIML)将通常以微分方程约束形式的先验物理信息集成到将机器学习模型拟合到物理数据的过程中。流行的PIML方法,包括神经算子,物理信息神经网络,神经常微分方程和神经离散平衡,通常适合同时包括数据和物理约束的目标。然而,这种方法的多目标性质在模型质量的测量中产生了模糊性。这与对认知不确定性的理解不佳有关,即使现有的统计指标表明很好的拟合,它也可能导致令人惊讶的失败模式。工作在一个高斯过程回归框架内,我们介绍了物理信息日志证据(PILE)得分。为了消除测试损失的模糊性,PILE分数是一个单一的、不确定性感知的度量,它为PIML模型的超参数提供了选择原则。我们表明,PILE最小化产生了各种各样的模型参数,包括内核带宽,最小二乘正则化权重,甚至核函数的选择很好的选择。我们还表明,即使在数据采集之前,一个特殊的“无数据”的情况下,PILE得分确定先验内核的选择,是“良好适应”一个给定的PDE。除了内核设置之外,我们预计PILE评分可以扩展到PIML,我们概述了这样做的方法。

英文摘要:

Physics-informed machine learning (PIML) integrates prior physical information, often in the form of differential equation constraints, into the process of fitting machine learning models to physical data. Popular PIML approaches, including neural operators, physics-informed neural networks, neural ordinary differential equations, and neural discrete equilibria, are typically fit to objectives that simultaneously include both data and physical constraints. However, the multi-objective nature of this approach creates ambiguity in the measurement of model quality. This is related to a poor understanding of epistemic uncertainty, and it can lead to surprising failure modes, even when existing statistical metrics suggest strong fits. Working within a Gaussian process regression framework, we introduce the Physics-Informed Log Evidence (PILE) score. Bypassing the ambiguities of test losses, the PILE score is a single, uncertainty-aware metric that provides a selection principle for hyperparameters of a PIML model. We show that PILE minimization yields excellent choices for a wide variety of model parameters, including kernel bandwidth, least squares regularization weights, and even kernel function selection. We also show that, even prior to data acquisition, a special 'data-free' case of the PILE score identifies a priori kernel choices that are 'well-adapted' to a given PDE. Beyond the kernel setting, we anticipate that the PILE score can be extended to PIML at large, and we outline approaches to do so.

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。

↑