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 2412.13403math.OC
收藏

基于QP的约束优化用于可靠的PINN训练

QP Based Constrained Optimization for Reliable PINN Training

Alan Williams, Christopher Leon, Alexander Scheinker

AI总结:

本文提出一种基于二次规划的约束优化训练方案,通过动态平衡数据损失与PDE残差损失,简化损失函数设计并保证收敛至最优参数,有效解决了PINNs训练中的收敛与稳定性问题。

摘要:

物理信息神经网络(PINNs)已成为整合基于物理的约束与数据以解决机器学习中正向与逆问题的强大工具。尽管具有潜力,但PINNs的实施受到若干挑战的阻碍,包括与收敛性、稳定性以及神经网络和损失函数设计相关的问题。在本文中,我们引入了一种新颖的训练方案,通过将训练过程构建为约束优化问题来解决这些挑战。利用基于二次规划(QP)的梯度下降法,我们的方法简化了损失函数的设计,并保证收敛到最优的神经网络参数。该方法论在训练过程中实现了基于数据的损失与偏微分方程(PDE)残差损失之间的动态平衡,在确保可接受准确度的同时,优先考虑最小化基于PDE的损失。我们在具有复杂几何形状的电容器中求解Laplace方程的背景下,展示了带有噪声数据的约束PINNs方法的公式化。这项工作不仅提升了PINNs的能力,还为它们的训练提供了一个框架。

英文摘要:

Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for integrating physics-based constraints and data to address forward and inverse problems in machine learning. Despite their potential, the implementation of PINNs are hampered by several challenges, including issues related to convergence, stability, and the design of neural networks and loss functions. In this paper, we introduce a novel training scheme that addresses these challenges by framing the training process as a constrained optimization problem. Utilizing a quadratic program (QP)-based gradient descent law, our approach simplifies the design of loss functions and guarantees convergences to optimal neural network parameters. This methodology enables dynamic balancing, over the course of training, between data-based loss and a partial differential equation (PDE) residual loss, ensuring an acceptable level of accuracy while prioritizing the minimization of PDE-based loss. We demonstrate the formulation of the constrained PINNs approach with noisy data, in the context of solving Laplace's equation in a capacitor with complex geometry. This work not only advances the capabilities of PINNs but also provides a framework for their training.

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。

↑