A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations

• URL: http://arxiv.org/abs/2101.01708v2
• Date: Mon, 22 Mar 2021 14:58:28 GMT
• Title: A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
• Authors: Jianfeng Lu, Yulong Lu, Min Wang
• Abstract summary: We derive the generalization error bounds of two-layer neural networks in the framework of the Deep Ritz Method (DRM) We prove that the convergence rates of generalization errors are independent of the dimension $d$. We develop a new solution theory for the PDEs on the spectral Barron space.
• Score: 11.974322921837384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper concerns the a priori generalization analysis of the Deep Ritz Method (DRM) [W. E and B. Yu, 2017], a popular neural-network-based method for solving high dimensional partial differential equations. We derive the generalization error bounds of two-layer neural networks in the framework of the DRM for solving two prototype elliptic PDEs: Poisson equation and static Schr\"odinger equation on the $d$-dimensional unit hypercube. Specifically, we prove that the convergence rates of generalization errors are independent of the dimension $d$, under the a priori assumption that the exact solutions of the PDEs lie in a suitable low-complexity space called spectral Barron space. Moreover, we give sufficient conditions on the forcing term and the potential function which guarantee that the solutions are spectral Barron functions. We achieve this by developing a new solution theory for the PDEs on the spectral Barron space, which can be viewed as an analog of the classical Sobolev regularity theory for PDEs.

Related papers

• Unisolver: PDE-Conditional Transformers Are Universal PDE Solvers [55.0876373185983]
  We present the Universal PDE solver (Unisolver) capable of solving a wide scope of PDEs. Our key finding is that a PDE solution is fundamentally under the control of a series of PDE components. Unisolver achieves consistent state-of-the-art results on three challenging large-scale benchmarks.
  arXiv  Detail & Related papers  (2024-05-27T15:34:35Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Approximation of Solution Operators for High-dimensional PDEs [2.3076986663832044]
  We propose a finite-dimensional control-based method to approximate solution operators for evolutional partial differential equations. Results are presented for several high-dimensional PDEs, including real-world applications to solving Hamilton-Jacobi-Bellman equations.
  arXiv  Detail & Related papers  (2024-01-18T21:45:09Z)
• Deep Equilibrium Based Neural Operators for Steady-State PDEs [100.88355782126098]
  We study the benefits of weight-tied neural network architectures for steady-state PDEs. We propose FNO-DEQ, a deep equilibrium variant of the FNO architecture that directly solves for the solution of a steady-state PDE.
  arXiv  Detail & Related papers  (2023-11-30T22:34:57Z)
• Error Analysis of Kernel/GP Methods for Nonlinear and Parametric PDEs [16.089904161628258]
  We introduce a priori Sobolev-space error estimates for the solution of nonlinear, and possibly parametric, PDEs. The proof is articulated around Sobolev norm error estimates for kernel interpolants. The error estimates demonstrate dimension-benign convergence rates if the solution space of the PDE is smooth enough.
  arXiv  Detail & Related papers  (2023-05-08T18:00:33Z)
• Solving High-Dimensional PDEs with Latent Spectral Models [74.1011309005488]
  We present Latent Spectral Models (LSM) toward an efficient and precise solver for high-dimensional PDEs. Inspired by classical spectral methods in numerical analysis, we design a neural spectral block to solve PDEs in the latent space. LSM achieves consistent state-of-the-art and yields a relative gain of 11.5% averaged on seven benchmarks.
  arXiv  Detail & Related papers  (2023-01-30T04:58:40Z)
• DiffNet: Neural Field Solutions of Parametric Partial Differential Equations [30.80582606420882]
  We consider a mesh-based approach for training a neural network to produce field predictions of solutions to PDEs. We use a weighted Galerkin loss function based on the Finite Element Method (FEM) on a parametric elliptic PDE. We prove theoretically, and illustrate with experiments, convergence results analogous to mesh convergence analysis deployed in finite element solutions to PDEs.
  arXiv  Detail & Related papers  (2021-10-04T17:59:18Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• On the Representation of Solutions to Elliptic PDEs in Barron Spaces [9.875204185976777]
  This paper derives complexity estimates of the solutions of $d$dimensional second-order elliptic PDEs in the Barron space. As a direct consequence of the complexity estimates, the solution of the PDE can be approximated on any bounded domain by a two-layer neural network.
  arXiv  Detail & Related papers  (2021-06-14T16:05:07Z)
• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory [4.243322291023028]
  We show that the gradient descent method can identify a global minimizer of the least-squares optimization for solving second-order linear PDEs. We also analyze the generalization error of the least-squares optimization for second-order linear PDEs and two-layer neural networks.
  arXiv  Detail & Related papers  (2020-06-28T22:24:51Z)
• Convex Geometry and Duality of Over-parameterized Neural Networks [70.15611146583068]
  We develop a convex analytic approach to analyze finite width two-layer ReLU networks. We show that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set. In higher dimensions, we show that the training problem can be cast as a finite dimensional convex problem with infinitely many constraints.
  arXiv  Detail & Related papers  (2020-02-25T23:05:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.