Solving Roughly Forced Nonlinear PDEs via Misspecified Kernel Methods and Neural Networks

• URL: http://arxiv.org/abs/2501.17110v2
• Date: Wed, 29 Jan 2025 20:21:48 GMT
• Title: Solving Roughly Forced Nonlinear PDEs via Misspecified Kernel Methods and Neural Networks
• Authors: Ricardo Baptista, Edoardo Calvello, Matthieu Darcy, Houman Owhadi, Andrew M. Stuart, Xianjin Yang,
• Abstract summary: We consider the use of Gaussian Processes (GPs) or Neural Networks (NNs) to numerically approximate the solutions to nonlinear partial differential equations (PDEs) We propose a generalization of these methods to handle roughly forced nonlinear PDEs while preserving convergence guarantees with an oversmoothing GP kernel. This is equivalent to replacing the empirical $L2$-loss on the PDE constraint by an empirical negative-Sobolev norm.
• Score: 3.1895609521267563
• License:
• Abstract: We consider the use of Gaussian Processes (GPs) or Neural Networks (NNs) to numerically approximate the solutions to nonlinear partial differential equations (PDEs) with rough forcing or source terms, which commonly arise as pathwise solutions to stochastic PDEs. Kernel methods have recently been generalized to solve nonlinear PDEs by approximating their solutions as the maximum a posteriori estimator of GPs that are conditioned to satisfy the PDE at a finite set of collocation points. The convergence and error guarantees of these methods, however, rely on the PDE being defined in a classical sense and its solution possessing sufficient regularity to belong to the associated reproducing kernel Hilbert space. We propose a generalization of these methods to handle roughly forced nonlinear PDEs while preserving convergence guarantees with an oversmoothing GP kernel that is misspecified relative to the true solution's regularity. This is achieved by conditioning a regular GP to satisfy the PDE with a modified source term in a weak sense (when integrated against a finite number of test functions). This is equivalent to replacing the empirical $L^2$-loss on the PDE constraint by an empirical negative-Sobolev norm. We further show that this loss function can be used to extend physics-informed neural networks (PINNs) to stochastic equations, thereby resulting in a new NN-based variant termed Negative Sobolev Norm-PINN (NeS-PINN).

Related papers

• Gaussian Process Priors for Boundary Value Problems of Linear Partial Differential Equations [3.524869467682149]
  Solving systems of partial differential equations (PDEs) is a fundamental task in computational science. Recent advancements have introduced neural operators and physics-informed neural networks (PINNs) to tackle PDEs. We propose a novel framework for constructing GP priors that satisfy both general systems of linear PDEs with constant coefficients and linear boundary conditions.
  arXiv  Detail & Related papers  (2024-11-25T18:48:15Z)
• 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)
• RoPINN: Region Optimized Physics-Informed Neural Networks [66.38369833561039]
  Physics-informed neural networks (PINNs) have been widely applied to solve partial differential equations (PDEs) This paper proposes and theoretically studies a new training paradigm as region optimization. A practical training algorithm, Region Optimized PINN (RoPINN), is seamlessly derived from this new paradigm.
  arXiv  Detail & Related papers  (2024-05-23T09:45:57Z)
• 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)
• 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)
• Physics-Informed Neural Operator for Learning Partial Differential Equations [55.406540167010014]
  PINO is the first hybrid approach incorporating data and PDE constraints at different resolutions to learn the operator. The resulting PINO model can accurately approximate the ground-truth solution operator for many popular PDE families.
  arXiv  Detail & Related papers  (2021-11-06T03:41:34Z)
• 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)
• Semi-Implicit Neural Solver for Time-dependent Partial Differential Equations [4.246966726709308]
  We propose a neural solver to learn an optimal iterative scheme in a data-driven fashion for any class of PDEs. We provide theoretical guarantees for the correctness and convergence of neural solvers analogous to conventional iterative solvers.
  arXiv  Detail & Related papers  (2021-09-03T12:03:10Z)
• Solving and Learning Nonlinear PDEs with Gaussian Processes [11.09729362243947]
  We introduce a simple, rigorous, and unified framework for solving nonlinear partial differential equations. The proposed approach provides a natural generalization of collocation kernel methods to nonlinear PDEs and IPs. For IPs, while the traditional approach has been to iterate between the identifications of parameters in the PDE and the numerical approximation of its solution, our algorithm tackles both simultaneously.
  arXiv  Detail & Related papers  (2021-03-24T03:16:08Z)
• 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)

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.