# A Priori Generalization Error Analysis of Two-Layer Neural Networks for Solving High Dimensional Schrödinger Eigenvalue Problems

This paper analyzes the generalization error of two-layer neural networks for computing the ground state of the Schrödinger operator on a d-dimensional hypercube. We prove that the convergence rate of the generalization error is independent of the dimension d, under the a priori assumption that the ground state lies in a spectral Barron space. We verify such assumption by proving a new regularity estimate for the ground state in the spectral Barron space. The later is achieved by a fixed point argument based on the Krein-Rutman theorem.

There are no comments yet.

## Authors

• 62 publications
• 11 publications
• ### A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations

This paper concerns the a priori generalization analysis of the Deep Rit...
01/05/2021 ∙ by Jianfeng Lu, et al. ∙ 0

• ### Optimal error estimation of a time-spectral method for fractional diffusion problems with low regularity data

This paper is devoted to the error analysis of a time-spectral algorithm...
06/06/2021 ∙ by Hao Luo, et al. ∙ 0

• ### A Look at the Effect of Sample Design on Generalization through the Lens of Spectral Analysis

This paper provides a general framework to study the effect of sampling ...
06/06/2019 ∙ by Bhavya Kailkhura, et al. ∙ 0

• ### A Priori Estimates of the Generalization Error for Two-layer Neural Networks

New estimates for the generalization error are established for the two-l...
10/15/2018 ∙ by Weinan E, et al. ∙ 0

• ### A priori generalization error for two-layer ReLU neural network through minimum norm solution

We focus on estimating a priori generalization error of two-layer ReLU n...
12/06/2019 ∙ by Zhi-Qin John Xu, et al. ∙ 0

• ### Spectral radii of asymptotic mappings and the convergence speed of the standard fixed point algorithm

Important problems in wireless networks can often be solved by computing...
03/15/2018 ∙ by Renato L. G. Cavalcante, et al. ∙ 0