PulseAugur
实时 19:42:59
None Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization

新的优化技术提高了复杂物理神经网络的精度

研究人员开发了一种名为 SOAP+GN 的新优化技术,以提高物理信息神经网络 (PINNs) 在处理复杂耦合多物理场系统时的精度。该方法解决了 PINN 精度随着方程间耦合增强而下降的已知问题。通过采用 Kronecker 预处理优化和逆梯度范数损失平衡,SOAP+GN 在大量实验中表现出鲁棒的精度,即使在以前标准优化方法(如 Adam+GN)不堪重负的挑战性二维系统中也是如此。 AI

影响 引入了一种新颖的优化方法,显著提高了物理信息神经网络在复杂多物理场模拟中的性能和适用性。

排序理由 学术论文,详细介绍了一种用于物理信息神经网络的新优化方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 · Youngjae Park, Jaemin Kim, Junghwa Hong ·

    Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization

    arXiv:2605.23391v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) for coupled multiphysics systems suffer systematic accuracy degradation as inter-equation coupling strengthens. We provide a theoretical explanation for this phenomenon through neural tangent…

  2. arXiv cs.LG TIER_1 · Junghwa Hong ·

    Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization

    Physics-informed neural networks (PINNs) for coupled multiphysics systems suffer systematic accuracy degradation as inter-equation coupling strengthens. We provide a theoretical explanation for this phenomenon through neural tangent kernel (NTK) analysis: for linearly coupled sys…