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 2402.11126cs.LGphysics.comp-ph
收藏

多任务物理信息机器学习(PIML)方法的柯尔莫哥洛夫 n-宽度:迈向稳健度量

Kolmogorov n-Widths for Multitask Physics-Informed Machine Learning (PIML) Methods: Towards Robust Metrics

Scientific Computing and Imaging Institute, University of Utah(犹他大学科学计算与成像研究所);Kahlert School of Computing, University of Utah(犹他大学卡勒特计算学院);Department of Computing and Mathematical Sciences, Caltech(加州理工学院计算与数学科学系)

Michael Penwarden, Houman Owhadi, Robert M. Kirby

AI总结:

本文提出以柯尔莫哥洛夫 n-宽度作为首个客观度量,用于比较多任务物理信息机器学习架构,并通过正则化将其纳入优化过程,从而提升模型在多任务 PDE 问题上的泛化能力。

摘要:

物理信息机器学习(PIML)作为求解偏微分方程(PDE)的一种手段,在计算科学与工程(CS&E)领域引起了广泛关注。该主题涵盖了大量旨在求解单个或一组 PDE 问题的方法和模型,后者被称为多任务学习。PIML 的特点是在求解 PDE 问题时,将物理定律纳入机器学习模型的训练过程,以替代大规模数据。尽管这类方法总体上取得了成功,但要对不同方法进行分析、基准测试和一般性比较仍然极其困难。我们利用柯尔莫哥洛夫 n-宽度作为逼近函数有效性的度量,审慎地将该度量应用于各种多任务 PIML 架构的比较中。我们计算了精度下界,并在各种 PDE 问题上分析了模型学习到的基函数。这是首个用于比较多任务 PIML 架构的客观度量,有助于消除因选择性采样和过拟合而导致的模型验证不确定性。我们还识别了模型架构的改进途径,例如激活函数的选择,它会极大地影响模型对“最坏情况”场景的泛化能力,而这种影响在报告特定任务误差时是无法观察到的。我们还将该度量通过正则化纳入优化过程,从而提高了模型在多任务 PDE 问题上的泛化能力。

英文摘要:

Physics-informed machine learning (PIML) as a means of solving partial differential equations (PDE) has garnered much attention in the Computational Science and Engineering (CS&E) world. This topic encompasses a broad array of methods and models aimed at solving a single or a collection of PDE problems, called multitask learning. PIML is characterized by the incorporation of physical laws into the training process of machine learning models in lieu of large data when solving PDE problems. Despite the overall success of this collection of methods, it remains incredibly difficult to analyze, benchmark, and generally compare one approach to another. Using Kolmogorov n-widths as a measure of effectiveness of approximating functions, we judiciously apply this metric in the comparison of various multitask PIML architectures. We compute lower accuracy bounds and analyze the model's learned basis functions on various PDE problems. This is the first objective metric for comparing multitask PIML architectures and helps remove uncertainty in model validation from selective sampling and overfitting. We also identify avenues of improvement for model architectures, such as the choice of activation function, which can drastically affect model generalization to "worst-case" scenarios, which is not observed when reporting task-specific errors. We also incorporate this metric into the optimization process through regularization, which improves the models' generalizability over the multitask PDE problem.

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。

↑