On the Representation of Solutions to Elliptic PDEs in Barron Spaces

• URL: http://arxiv.org/abs/2106.07539v1
• Date: Mon, 14 Jun 2021 16:05:07 GMT
• Title: On the Representation of Solutions to Elliptic PDEs in Barron Spaces
• Authors: Ziang Chen, Jianfeng Lu, Yulong Lu
• Abstract summary: 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.
• Score: 9.875204185976777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Numerical solutions to high-dimensional partial differential equations (PDEs) based on neural networks have seen exciting developments. This paper derives complexity estimates of the solutions of $d$-dimensional second-order elliptic PDEs in the Barron space, that is a set of functions admitting the integral of certain parametric ridge function against a probability measure on the parameters. We prove under some appropriate assumptions that if the coefficients and the source term of the elliptic PDE lie in Barron spaces, then the solution of the PDE is $\epsilon$-close with respect to the $H^1$ norm to a Barron function. Moreover, we prove dimension-explicit bounds for the Barron norm of this approximate solution, depending at most polynomially on the dimension $d$ of the PDE. 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 with respect to the $H^1$ norm with a dimension-explicit convergence rate.

Related papers

• Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for space-time solutions of semilinear partial differential equations [3.3123773366516645]
  It is a challenging topic in applied mathematics to solve high-dimensional nonlinear partial differential equations (PDEs) Deep learning (DL) based methods for PDEs in which deep neural networks (DNNs) are used to approximate solutions of PDEs are presented.
  arXiv  Detail & Related papers  (2024-06-16T09:59:29Z)
• 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)
• 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)
• Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective [40.964402478629495]
  We take a step towards studying the representational power of neural networks for approximating solutions to nonlinear PDEs. Treating a class of PDEs known as emphnonlinear elliptic variational PDEs, our results show neural networks can evade the curse of dimensionality.
  arXiv  Detail & Related papers  (2022-10-21T16:53:18Z)
• Learning differentiable solvers for systems with hard constraints [48.54197776363251]
  We introduce a practical method to enforce partial differential equation (PDE) constraints for functions defined by neural networks (NNs) We develop a differentiable PDE-constrained layer that can be incorporated into any NN architecture. Our results show that incorporating hard constraints directly into the NN architecture achieves much lower test error when compared to training on an unconstrained objective.
  arXiv  Detail & Related papers  (2022-07-18T15:11:43Z)
• Lie Point Symmetry Data Augmentation for Neural PDE Solvers [69.72427135610106]
  We present a method, which can partially alleviate this problem, by improving neural PDE solver sample complexity. In the context of PDEs, it turns out that we are able to quantitatively derive an exhaustive list of data transformations. We show how it can easily be deployed to improve neural PDE solver sample complexity by an order of magnitude.
  arXiv  Detail & Related papers  (2022-02-15T18:43:17Z)
• dNNsolve: an efficient NN-based PDE solver [62.997667081978825]
  We introduce dNNsolve, that makes use of dual Neural Networks to solve ODEs/PDEs. We show that dNNsolve is capable of solving a broad range of ODEs/PDEs in 1, 2 and 3 spacetime dimensions.
  arXiv  Detail & Related papers  (2021-03-15T19:14:41Z)
• A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations [11.974322921837384]
  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.
  arXiv  Detail & Related papers  (2021-01-05T18:50:59Z)
• 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)
• Space-time deep neural network approximations for high-dimensional partial differential equations [3.6185342807265415]
  Deep learning approximations might have the capacity to overcome the curse of dimensionality. This article proves for every $ainmathbbR$, $ bin (a,infty)$ that solutions of certain Kolmogorov PDEs can be approximated by DNNs without the curse of dimensionality.
  arXiv  Detail & Related papers  (2020-06-03T12:14:56Z)

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.