arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05800math.NAcs.NA
收藏

基于局部随机神经网络的扰动校正方法用于拟线性界面问题

A Perturbation-Correction Method Based on Local Randomized Neural Networks for Quasi-Linear Interface Problems

School of Mathematical Sciences, Ministry of Education Key Laboratory of NSLSCS, Nanjing Normal University(南京师范大学数学科学学院,教育部非光滑分析与应用重点实验室)

Siyuan Lang, Zhiyue Zhang

AI总结:

针对拟线性椭圆界面问题,提出一种局部随机神经网络扰动校正方法(LRaNN-PC),通过主阶段和扰动校正阶段缓解非凸目标泛函导致的停滞,数值实验显示相对L2误差降低4-7个数量级。

摘要:

对于具有不连续扩散系数的拟线性椭圆界面问题,随机神经网络近似可能由于相关目标泛函通常非凸而出现停滞。本文提出一种局部随机神经网络(LRaNN)扰动校正方法,记为LRaNN-PC,以缓解这种停滞。该方法在区域分解框架下,通过界面条件耦合,在每个子域上使用LRaNN表示解。它由一个主阶段和一个扰动校正(PC)阶段组成。主阶段通过最小化原始非凸目标泛函计算主近似。PC阶段通过围绕主近似进行残差的局部展开,并在独立生成的随机试验空间中表示校正,构建残差驱动的校正。校正系数通过在该试验空间中求解最小二乘残差校正子问题获得。对于所陈述的充分假设下依赖于解的拟线性椭圆模型,我们推导了破碎$H^1$半范数误差的残差控制上界。该上界涉及离散残差、求积误差、扰动校正子问题的残差以及扰动展开的截断余项。数值实验进一步测试了该设置下的不规则界面和高对比度系数,并检验了梯度依赖扩散系数和移动界面扩展。在测试的基准问题中,与主LRaNN阶段相比,LRaNN-PC将相对$L^2$误差降低了高达4-7个数量级。

英文摘要:

For quasi-linear elliptic interface problems with discontinuous diffusion coefficients, randomized neural network approximations may exhibit stagnation because the associated objective functional is generally nonconvex. This paper proposes a Local Randomized Neural Network (LRaNN) perturbation-correction method, denoted by LRaNN-PC, to alleviate this stagnation. The method represents the solution using an LRaNN on each subdomain, coupled through the interface conditions in a domain-decomposed framework. It consists of a primary stage and a perturbation-correction (PC) stage. The primary stage computes the primary approximation by minimizing the original nonconvex objective functional. The PC stage constructs a residual-driven correction by performing a local expansion of the residual around the primary approximation and representing the correction in an independently generated randomized trial space. The correction coefficients are obtained by solving a least-squares residual-correction subproblem in this trial space. For the solution-dependent quasi-linear elliptic model under the stated sufficient assumptions, we derive a residual-controlled upper bound for the broken $H^1$ seminorm error. The bound involves the discrete residual, the quadrature error, the residual of the perturbation-correction subproblem, and the truncation remainder of the perturbation expansion. Numerical experiments further test irregular interfaces and high-contrast coefficients within this setting, and also examine gradient-dependent diffusivities and moving-interface extensions. In the tested benchmarks, LRaNN-PC reduces the relative $L^2$ error by up to $4$--$7$ orders of magnitude compared with the primary LRaNN stage.

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。

↑