Learned Lagrangian Models of PDEs via Euler-Lagrange Residual Minimization

• URL: http://arxiv.org/abs/2605.07157v1
• Date: Fri, 08 May 2026 02:43:11 GMT
• Title: Learned Lagrangian Models of PDEs via Euler-Lagrange Residual Minimization
• Abstract summary: We present the first method to directly use a learned continuous Lagrangian to forecast the dynamics of systems governed by partial differential equations.<n>We develop an optimization-based integrator that minimizes the squared Euler-Lagrange residual.<n>We validate our approach on a learned representation of a double pendulum, a one-dimensional wave equation, and a two-dimensional wave equation.
• Score: 6.069579199180933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present the first method to directly use a learned continuous Lagrangian to forecast the dynamics of systems governed by partial differential equations, exploiting the inherent conservative structure to achieve stable long-range predictions. We develop an optimization-based integrator that minimizes the squared Euler--Lagrange residual via a mesh-free near-symplectic construction on local space-time patches. Different from integrators for analytical models, integrators for learned models should decouple model error (phase error) from integration error (conservation error). By relying on optimization rather than time-stepping, we bypass the global coupling inherent to fixed discretizations, which slows time- and space-stepping and complicates learning. Our method scales linearly with domain size via Jacobi iteration, and places no structural requirements on the learned network, allowing it to be coupled with existing physics-guided machine learning (ML) methods. We validate our approach on a learned representation of a double pendulum, a one-dimensional wave equation, and a two-dimensional wave equation. Our method achieves error comparable to classical symplectic methods while generalizing to spatially varying dynamics and arbitrary boundary conditions without retraining.

Related papers

• Emulating Cosmic Structure Formation with a Lagrangian Neural Cellular Automaton [0.0]
  We introduce a hybrid deep learning framework that can be applied to structure formation as a local, iterative dynamical process on a comoving lattice.<n>By training the network to learn only the textitresidual displacement corrections to the Zeldovich approximation, we achieve high-fidelity emulation of the non-linear physics.<n>Our trained model supports percent-level precision in the power and cross spectra well into the non-linear regime.
  arXiv  Detail & Related papers  (2026-07-29T18:00:01Z)
• Circuit Depth Reduction of One-Ancilla Quantum Differential Equation Solver via Extrapolation [1.0742675209112622]
  A recent one-ancilla quantum differential equation solver provides a hardware-friendly and locality-preserving approach.<n>We reduce the maximum single-run circuit depth to $O(mathrmpolylog (1/)$ without adding quantum ancillae or sacrificing locality.<n> Numerical experiments on the Hatano-Nelson model (ODE) and the convection-diffusion equation (PDE) demonstrate the effectiveness of the approach.
  arXiv  Detail & Related papers  (2026-07-08T13:20:43Z)
• Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation [55.88862563823878]
  In this work, we present an original algorithm to coarsen an unstructured grid based on the concepts of differentiable physics.<n>We demonstrate performance of the algorithm on two PDEs: a linear equation which governs slightly compressible fluid flow in porous media and the wave equation.<n>Our results show that in the considered scenarios, we reduced the number of grid points up to 10 times while preserving the modeled variable dynamics in the points of interest.
  arXiv  Detail & Related papers  (2025-07-24T11:02:13Z)
• Data-Driven Adaptive Gradient Recovery for Unstructured Finite Volume Computations [0.0]
  We present a novel data-driven approach for enhancing gradient reconstruction in unstructured finite volume methods for hyperbolic conservation laws.<n>Our approach extends previous structured-grid methodologies to unstructured meshes through a modified DeepONet architecture.<n>The proposed algorithm is faster and more accurate than the traditional second-order finite volume solver.
  arXiv  Detail & Related papers  (2025-07-22T13:23:57Z)
• A Model-Constrained Discontinuous Galerkin Network (DGNet) for Compressible Euler Equations with Out-of-Distribution Generalization [0.0]
  We develop a model-constrained discontinuous Galerkin Network (DGNet) approach.<n>The core of DGNet is the synergy of several key strategies.<n>We present comprehensive numerical results for 1D and 2D compressible Euler equation problems.
  arXiv  Detail & Related papers  (2024-09-27T01:13:38Z)
• A domain decomposition-based autoregressive deep learning model for unsteady and nonlinear partial differential equations [2.7755345520127936]
  We propose a domain-decomposition-based deep learning (DL) framework, named CoMLSim, for accurately modeling unsteady and nonlinear partial differential equations (PDEs)<n>The framework consists of two key components: (a) a convolutional neural network (CNN)-based autoencoder architecture and (b) an autoregressive model composed of fully connected layers.
  arXiv  Detail & Related papers  (2024-08-26T17:50:47Z)
• Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds [0.559239450391449]
  We present two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems. The addition of quadratic terms to the state approximation, which sits at the heart of the proposed methodologies, enables us to better represent intrinsic low-dimensionality.
  arXiv  Detail & Related papers  (2023-05-24T18:23:25Z)
• Semi-supervised Learning of Partial Differential Operators and Dynamical Flows [68.77595310155365]
  We present a novel method that combines a hyper-network solver with a Fourier Neural Operator architecture. We test our method on various time evolution PDEs, including nonlinear fluid flows in one, two, and three spatial dimensions. The results show that the new method improves the learning accuracy at the time point of supervision point, and is able to interpolate and the solutions to any intermediate time.
  arXiv  Detail & Related papers  (2022-07-28T19:59:14Z)
• Optimization on manifolds: A symplectic approach [127.54402681305629]
  We propose a dissipative extension of Dirac's theory of constrained Hamiltonian systems as a general framework for solving optimization problems. Our class of (accelerated) algorithms are not only simple and efficient but also applicable to a broad range of contexts.
  arXiv  Detail & Related papers  (2021-07-23T13:43:34Z)
• A Discrete Variational Derivation of Accelerated Methods in Optimization [68.8204255655161]
  We introduce variational which allow us to derive different methods for optimization. We derive two families of optimization methods in one-to-one correspondence. The preservation of symplecticity of autonomous systems occurs here solely on the fibers.
  arXiv  Detail & Related papers  (2021-06-04T20:21:53Z)
• The Connection between Discrete- and Continuous-Time Descriptions of Gaussian Continuous Processes [60.35125735474386]
  We show that discretizations yielding consistent estimators have the property of invariance under coarse-graining' This result explains why combining differencing schemes for derivatives reconstruction and local-in-time inference approaches does not work for time series analysis of second or higher order differential equations.
  arXiv  Detail & Related papers  (2021-01-16T17:11:02Z)
• Optimal oracle inequalities for solving projected fixed-point equations [53.31620399640334]
  We study methods that use a collection of random observations to compute approximate solutions by searching over a known low-dimensional subspace of the Hilbert space. We show how our results precisely characterize the error of a class of temporal difference learning methods for the policy evaluation problem with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-09T20:19:32Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

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.