Problem
Research questions and friction points this paper is trying to address.
operator eigenvalue problem
neural eigenvalue solver
high-dimensional problems
finite difference method
Low-Fidelity FDM Spectral Guidance for Neural Eigenvalue Solvers
🤖 AI Summary
This study addresses the computational expense of traditional methods and the training inefficiency and instability of purely neural approaches for solving high-dimensional operator eigenvalue problems. To overcome these challenges, we propose the Stable Inverse Power Method Neural Network (SIPMNN). This method introduces a novel low-fidelity numerical spectral guidance mechanism, employing coarse-grid finite difference approximations to generate approximate eigenvalues as fixed shifts that guide and constrain the deep neural network training process. Experimental results on ten-dimensional benchmark problems demonstrate that SIPMNN achieves superior solution accuracy compared to purely neural baselines while reducing the required number of iterations by eight- to tenfold. Consequently, this work effectively resolves the bottlenecks associated with high-dimensional eigenvalue search difficulties and training instability.
📝 Abstract
Operator eigenvalue problems appear throughout science. Classical methods usually discretize the operator into a matrix and then solve the resulting matrix eigenvalue problem. This works well in low dimensions, but fine grids quickly become expensive in both memory and computation as the dimension grows. Neural network based solvers avoid storing these large grids, but recent state of the art neural methods can require hundreds of thousands of training steps and may struggle to find the desired eigenvalues. We show that the two approaches can help each other. A coarse finite difference method (FDM) calculation acts as a cheap numerical model of the operator spectrum. We use the approximate eigenvalues as fixed shifts during the training of the neural solver, as they only need to locate the relevant part of the spectrum. We also introduce Stabilized Inverse Power Method Neural Network (SIPMNN), a more stable training procedure for higher-dimensional problems. Across five test problems at $d=10$, the combined approach is more accurate overall than the tested fully neural alternatives while using eight to ten times fewer iterations.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Neural Eigenvalue Solvers
Finite Difference Method
Spectral Guidance
Stabilized Inverse Power Method
Operator Eigenvalue Problems
🔎 Similar Papers
No similar papers found.
