高维偏微分方程的无偏和二阶自由训练
Unbiased and Second-Order-Free Training for High-Dimensional PDEs
AI总结:
本文提出一种无偏且二阶自由的训练框架,解决高维PDEs中BSDE训练的偏倚问题,保留了BSDE方法的计算优势。
摘要:
基于反向随机微分方程(BSDEs)的深度学习方法已成为求解高维偏微分方程(PDEs)的有力替代方案,相较于物理信息神经网络(PINNs)。通过利用概率表示,BSDE方法可以避免维度诅咒,通常允许无需显式Hessian评估的二阶自由训练目标。最近研究表明,常用的欧拉-马尔可夫(EM)时间离散化在BSDE训练损失中引入了内在偏倚。尽管高阶方案如Heun可完全消除此偏倚,但此类方案重新引入了二阶空间导数并带来显著的计算开销。本文提供了EM诱导损失偏倚的原理性分析,并提出了一种无偏、二阶自由的训练框架,保留了BSDE方法的计算优势。我们的代码可在https://github.com/seojaemin22/Un-EM-BSDE获取。
英文摘要:
Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By leveraging probabilistic representations, BSDE approaches can avoid the curse of dimensionality and often admit second-order-free training objectives that do not require explicit Hessian evaluations. It has recently been established that the commonly used Euler-Maruyama (EM) time discretization induces an intrinsic bias in BSDE training losses. While high-order schemes such as Heun can fully eliminate this bias, such schemes re-introduce second-order spatial derivatives and incur substantial computational overhead. In this work, we provide a principled analysis of EM-induced loss bias and propose an unbiased, second-order-free training framework that preserves the computational advantages of BSDE methods. Our code is available at https://github.com/seojaemin22/Un-EM-BSDE.
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。