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 2512.00564cs.LGphysics.flu-dyn
收藏

预生成多难度的PDE数据以用于少样本神经PDE求解器

Pre-Generating Multi-Difficulty PDE Data for Few-Shot Neural PDE Solvers

Machine Learning Department, Carnegie Mellon University(卡内基梅隆大学机器学习系);Department of Computer Sciences, UW-Madison(威斯康星大学麦迪逊分校计算机科学系)

Naman Choudhary, Vedant Singh, Ameet Talwalkar, Nicholas Matthew Boffi, Mikhail Khodak, Tanya Marwah

AI总结:

通过预生成多难度的PDE数据,提升少样本神经PDE求解器的性能与效率。

摘要:

学习偏微分方程(PDE)求解器的一个关键方面是,主要成本往往来自于用经典求解器生成训练数据,而不是学习模型本身。另一个方面是存在明显的难度轴——例如更复杂的几何形状和更高的雷诺数——沿这些轴线,问题变得(1)对经典求解器更难,因此(2)更有可能从神经求解器中受益。为了解决这个鸡生蛋的问题,我们研究了2D不可压缩纳维-斯托克斯方程上的难度转移,系统地沿几何(障碍物的数量和位置)、物理(雷诺数)以及它们的组合变化任务复杂性。类似于通过计算预训练基础模型以提高其在下游任务上的性能,我们发现通过经典求解(类比预生成)许多低和中等难度的例子并将它们包含在训练集中,可以学习到高难度的物理现象,而只需更少的样本。此外,我们还显示通过结合低和高难度的数据,可以在预生成数据集时花费8.9倍更少的计算量,以达到与仅使用高难度示例相同的效果。我们的结果强调了如何在难度级别上分配经典求解器的计算资源与总体分配量同样重要,并表明通过系统地预生成PDE数据以用于神经求解器,可以实现显著的收益。我们的代码可在https://github.com/Naman-Choudhary-AI-ML/pregenerating-pde上获得。

英文摘要:

A key aspect of learned partial differential equation (PDE) solvers is that the main cost often comes from generating training data with classical solvers rather than learning the model itself. Another is that there are clear axes of difficulty--e.g., more complex geometries and higher Reynolds numbers--along which problems become (1) harder for classical solvers and thus (2) more likely to benefit from neural speedups. Towards addressing this chicken-and-egg challenge, we study difficulty transfer on 2D incompressible Navier-Stokes, systematically varying task complexity along geometry (number and placement of obstacles), physics (Reynolds number), and their combination. Similar to how it is possible to spend compute to pre-train foundation models and improve their performance on downstream tasks, we find that by classically solving (analogously pre-generating) many low and medium difficulty examples and including them in the training set, it is possible to learn high-difficulty physics from far fewer samples. Furthermore, we show that by combining low and high difficulty data, we can spend 8.9x less compute on pre-generating a dataset to achieve the same error as using only high difficulty examples. Our results highlight that how we allocate classical-solver compute across difficulty levels is as important as how much we allocate overall, and suggest substantial gains from principled curation of pre-generated PDE data for neural solvers. Our code is available at https://github.com/Naman-Choudhary-AI-ML/pregenerating-pde

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。

↑