使用神经球面游走法求解泊松方程
Solving Poisson Equations using Neural Walk-on-Spheres
AI总结:
本文提出神经球面游走法NWoS,利用球面随机游走递归构造无需空间梯度的神经网络损失,高效求解高维泊松方程,在精度、速度和内存成本上显著优于PINNs等方法,并成功应用于PDE约束优化与分子动力学。
摘要:
我们提出神经球面游走法(Neural Walk-on-Spheres,NWoS),这是一种用于高效求解高维泊松方程的新型神经偏微分方程求解器。利用随机表示和球面游走(Walk-on-Spheres)方法,我们基于域内球面上泊松方程的递归求解,为神经网络开发了新的损失函数。所得到的方法高度可并行化,且损失函数不需要空间梯度。我们与基于PINNs、Deep Ritz方法以及(倒向)随机微分方程的竞争方法进行了全面比较。在若干具有挑战性的高维数值算例中,我们证明了NWoS在精度、速度和计算成本方面的优越性。与常用的PINNs相比,我们的方法可以将内存占用和误差降低数个数量级。此外,我们将NWoS应用于偏微分方程约束优化和分子动力学问题,以展示其在实际应用中的效率。
英文摘要:
We propose Neural Walk-on-Spheres (NWoS), a novel neural PDE solver for the efficient solution of high-dimensional Poisson equations. Leveraging stochastic representations and Walk-on-Spheres methods, we develop novel losses for neural networks based on the recursive solution of Poisson equations on spheres inside the domain. The resulting method is highly parallelizable and does not require spatial gradients for the loss. We provide a comprehensive comparison against competing methods based on PINNs, the Deep Ritz method, and (backward) stochastic differential equations. In several challenging, high-dimensional numerical examples, we demonstrate the superiority of NWoS in accuracy, speed, and computational costs. Compared to commonly used PINNs, our approach can reduce memory usage and errors by orders of magnitude. Furthermore, we apply NWoS to problems in PDE-constrained optimization and molecular dynamics to show its efficiency in practical applications.
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。