arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.01640math.APmath.OCmath.PR
收藏

Schrödinger特征值问题的两层神经网络

Two-layers neural networks for Schr{ö}dinger eigenvalue problems

CERMICS, École nationale des Ponts et Chaussées(国立路桥学校);INRIA Paris(巴黎国家数字研究院)

Mathias Dus, Virginie Ehrlacher

AI总结:

本文分析无限宽两层神经网络求解高维Schrödinger特征值问题,证明约束梯度曲线解的存在性及收敛时得到特征函数,首次处理非凸泛函极小化。

摘要:

本文旨在分析使用无限宽两层神经网络求解高维Schrödinger特征值问题的数值格式,该问题具有光滑相互作用势,并在任意维度的单位立方体上满足Neumann边界条件。更具体地,与Schrödinger算子最低特征值相关的任何特征函数都是相应能量的单位L2范数极小化子。利用Barron表示,将解表示为参数值集合上的概率测度,并遵循Bach和Chizat [1]最初提出的方法,通过在定义神经网络的参数值集合的2-Wasserstein空间上的约束梯度曲线动态来最小化能量。我们证明了该约束梯度曲线解的存在性。此外,我们证明,如果该曲线收敛,则所表示的函数即为所考虑的Schrödinger算子的特征函数。至少据我们所知,这是首次开展此类分析来处理非凸泛函极小化的工作。

英文摘要:

The aim of this article is to analyze numerical schemes using two-layer neural networks with infinite width for the resolution of high-dimensional Schr{ö}dinger eigenvalue problems with smooth interaction potentials and Neumann boundary condition on the unit cube in any dimension. More precisely, any eigenfunction associated to the lowest eigenvalue of the Schr{ö}dinger operator is a unit L 2 norm minimizer of the associated energy. Using Barron's representation of the solution with a probability measure defined on the set of parameter values and following the approach initially suggested by Bach and Chizat [1], the energy is minimized thanks to a constrained gradient curve dynamic on the 2-Wasserstein space of the set of parameter values defining the neural network. We prove the existence of solutions to this constrained gradient curve. Furthermore, we prove that, if it converges, the represented function is then an eigenfunction of the considered Schr{ö}dinger operator. At least up to our knowledge, this is the first work where this type of analysis is carried out to deal with the minimization of non-convex functionals.

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。

↑