Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities

• URL: http://arxiv.org/abs/2210.01074v1
• Date: Mon, 3 Oct 2022 16:47:56 GMT
• Title: Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities
• Authors: Samuel Lanthaler and Roberto Molinaro and Patrik Hadorn and Siddhartha Mishra
• Abstract summary: A large class of hyperbolic and advection-dominated PDEs can have solutions with discontinuities. We rigorously prove, in terms of lower approximation bounds, that methods which entail a linear reconstruction step fail to efficiently approximate the solution operator of such PDEs. We show that certain methods employing a non-linear reconstruction mechanism can overcome these fundamental lower bounds and approximate the underlying operator efficiently.
• Score: 5.735035463793008
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A large class of hyperbolic and advection-dominated PDEs can have solutions with discontinuities. This paper investigates, both theoretically and empirically, the operator learning of PDEs with discontinuous solutions. We rigorously prove, in terms of lower approximation bounds, that methods which entail a linear reconstruction step (e.g. DeepONet or PCA-Net) fail to efficiently approximate the solution operator of such PDEs. In contrast, we show that certain methods employing a non-linear reconstruction mechanism can overcome these fundamental lower bounds and approximate the underlying operator efficiently. The latter class includes Fourier Neural Operators and a novel extension of DeepONet termed shift-DeepONet. Our theoretical findings are confirmed by empirical results for advection equation, inviscid Burgers' equation and compressible Euler equations of aerodynamics.

Related papers

• A Deep Learning approach for parametrized and time dependent Partial Differential Equations using Dimensionality Reduction and Neural ODEs [46.685771141109306]
  We propose an autoregressive and data-driven method using the analogy with classical numerical solvers for time-dependent, parametric and (typically) nonlinear PDEs. We show that by leveraging DR we can deliver not only more accurate predictions, but also a considerably lighter and faster Deep Learning model.
  arXiv  Detail & Related papers  (2025-02-12T11:16:15Z)
• Quantitative Approximation for Neural Operators in Nonlinear Parabolic Equations [0.40964539027092917]
  We derive the approximation rate of solution operators for the nonlinear parabolic partial differential equations (PDEs) Our results show that neural operators can efficiently approximate these solution operators without the exponential growth in model complexity. A key insight in our proof is to transfer PDEs into the corresponding integral equations via Duahamel's principle, and to leverage the similarity between neural operators and Picard's iteration.
  arXiv  Detail & Related papers  (2024-10-03T02:28:17Z)
• Structure-preserving learning for multi-symplectic PDEs [8.540823673172403]
  This paper presents an energy-preserving machine learning method for inferring reduced-order models (ROMs) by exploiting the multi-symplectic form of partial differential equations (PDEs) We prove that the proposed method satisfies spatially discrete local energy conservation and preserves the multi-symplectic conservation laws.
  arXiv  Detail & Related papers  (2024-09-16T16:07:21Z)
• 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)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Deep Learning of Delay-Compensated Backstepping for Reaction-Diffusion PDEs [2.2869182375774613]
  Multiple operators arise in the control of PDE systems from distinct PDE classes. DeepONet-approximated nonlinear operator is a cascade/composition of the operators defined by one hyperbolic PDE of the Goursat form and one parabolic PDE on a rectangle. For the delay-compensated PDE backstepping controller, we guarantee exponential stability in the $L2$ norm of the plant state and the $H1$ norm of the input delay state.
  arXiv  Detail & Related papers  (2023-08-21T06:42:33Z)
• Learning Discretized Neural Networks under Ricci Flow [48.47315844022283]
  We study Discretized Neural Networks (DNNs) composed of low-precision weights and activations. DNNs suffer from either infinite or zero gradients due to the non-differentiable discrete function during training.
  arXiv  Detail & Related papers  (2023-02-07T10:51:53Z)
• 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)
• 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)
• Learning Fast Approximations of Sparse Nonlinear Regression [50.00693981886832]
  In this work, we bridge the gap by introducing the Threshold Learned Iterative Shrinkage Algorithming (NLISTA) Experiments on synthetic data corroborate our theoretical results and show our method outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-26T11:31:08Z)

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.