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 2601.08709math.NAcs.LGcs.NA
收藏

多预处理LBFGS用于训练有限基物理信息神经网络

Multi-Preconditioned LBFGS for Training Finite-Basis PINNs

Università della Svizzera Italiana(瑞士意大利大学);Toulouse INP-ENSEEIHT(图卢兹INP-ENSEEIHT);IRIT(IRIT研究所);ANITI(ANITI研究所);Delft Institute of Applied Mathematics(代尔夫特应用数学研究所);TU Delft(代尔夫特理工大学);King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹大学)

Marc Salvadó-Benasco, Aymane Kssim, Alexander Heinlein, Rolf Krause, Serge Gratton, Alena Kopaničáková

AI总结:

本文提出多预处理LBFGS算法用于训练有限基物理信息神经网络,通过域分解启发的加法架构局部化网络表示,结合非线性多预处理机制提升收敛速度和模型精度。

摘要:

本文介绍了一种多预处理LBFGS(MP-LBFGS)算法,用于训练有限基物理信息神经网络(FBPINNs)。该算法受非线性加性Schrödinger方法启发,利用FBPINNs的域分解启发的加法架构,其中局部神经网络定义在子域上,从而局部化网络表示。随后在相应架构的局部部分构建并行、子域局部的准牛顿修正。关键特征是新颖的非线性多预处理机制,其中子域修正通过求解低维子空间最小化问题最优组合。数值实验表明,MP-LBFGS在标准LBFGS上提高了收敛速度和模型精度,同时带来了更低的通信开销。

英文摘要:

A multi-preconditioned LBFGS (MP-LBFGS) algorithm is introduced for training finite-basis physics-informed neural networks (FBPINNs). The algorithm is motivated by the nonlinear additive Schwarz method and exploits the domain-decomposition-inspired additive architecture of FBPINNs, in which local neural networks are defined on subdomains, thereby localizing the network representation. Parallel, subdomain-local quasi-Newton corrections are then constructed on the corresponding local parts of the architecture. A key feature is a novel nonlinear multi-preconditioning mechanism, in which subdomain corrections are optimally combined through the solution of a low-dimensional subspace minimization problem. Numerical experiments indicate that MP-LBFGS can improve convergence speed, as well as model accuracy over standard LBFGS while incurring lower communication overhead.

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。

↑