Timezone: »

 
Statistical Numerical PDE : Fast Rate, Neural Scaling Law and When it’s Optimal
Yiping Lu · Haoxuan Chen · Jianfeng Lu · Lexing Ying · Jose Blanchet

Tue Dec 14 06:45 AM -- 07:30 AM (PST) @
in The Symbiosis of Deep Learning and Differential Equations »
Event URL: https://openreview.net/forum?id=fdhjOSmHQ2U »

In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs). To simplify the problem, we focus on a prototype elliptic PDE: the Schr\"odinger equation on a hypercube with zero Dirichlet boundary condition, which is applied in quantum-mechanical systems. We establish upper and lower bounds for both methods, which improve upon concurrently developed upper bounds for this problem via a fast rate generalization bound. We discover that the current Deep Ritz Method is sub-optimal and propose a modified version of it. We also prove that PINN and the modified version of DRM can achieve minimax optimal bounds over Sobolev spaces. Empirically, following recent work which has shown that the deep model accuracy will improve with growing training sets according to a power law, we supply computational experiments to show similar-behavior of dimension dependent power law for deep PDE solvers.

Author Information

Yiping Lu (Stanford University)
Haoxuan Chen (California Institute of Technology)
Jianfeng Lu (Duke University)
Lexing Ying (Stanford University)
Jose Blanchet (Stanford University)

More from the Same Authors