基于约束学习的微分方程求解
Solving Differential Equations with Constrained Learning
AI总结:
本文提出科学约束学习(SCL)框架,将PDE弱解求解等价转化为最坏情况损失的约束学习问题,从而在无需大量超参数调优的情况下实现精确求解。
摘要:
(偏)微分方程(PDE)是描述自然现象的基础工具,因此其求解在科学与工程中至关重要。虽然有限元法等传统方法能提供可靠解,但其精度往往依赖于计算密集的精细网格。此外,这些方法无法自然地利用测量数据或先验解,且问题参数一旦变化就需要完全重新计算。基于神经网络的方法,如物理信息神经网络和神经算子,通过直接将这些模型拟合到PDE解上,提供了一种无网格替代方案。它们还可以整合先验知识,并通过简单地聚合额外的训练损失来处理整个PDE族。然而,它们对配置点以及与每个损失相关的权重等超参数高度敏感。本文通过构建科学约束学习(SCL)框架来应对这些挑战。文中证明,寻找PDE的(弱)解等价于求解一个具有最坏情况损失的约束学习问题。这解释了以往最小化聚合损失期望值的方法的局限性。SCL还自然地整合了结构约束(例如不变性)以及(部分)测量数据或已知解。由此产生的约束学习问题可以通过一种实用算法来求解,该算法能够在各种PDE、神经网络架构和先验知识水平下得到精确解,无需大量超参数调优,有时甚至能以更低的计算成本实现。
英文摘要:
(Partial) differential equations (PDEs) are fundamental tools for describing natural phenomena, making their solution crucial in science and engineering. While traditional methods, such as the finite element method, provide reliable solutions, their accuracy is often tied to the use of computationally intensive fine meshes. Moreover, they do not naturally account for measurements or prior solutions, and any change in the problem parameters requires results to be fully recomputed. Neural network-based approaches, such as physics-informed neural networks and neural operators, offer a mesh-free alternative by directly fitting those models to the PDE solution. They can also integrate prior knowledge and tackle entire families of PDEs by simply aggregating additional training losses. Nevertheless, they are highly sensitive to hyperparameters such as collocation points and the weights associated with each loss. This paper addresses these challenges by developing a science-constrained learning (SCL) framework. It demonstrates that finding a (weak) solution of a PDE is equivalent to solving a constrained learning problem with worst-case losses. This explains the limitations of previous methods that minimize the expected value of aggregated losses. SCL also organically integrates structural constraints (e.g., invariances) and (partial) measurements or known solutions. The resulting constrained learning problems can be tackled using a practical algorithm that yields accurate solutions across a variety of PDEs, neural network architectures, and prior knowledge levels without extensive hyperparameter tuning and sometimes even at a lower computational cost.
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。