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.
| Comments: | 9 pages, 8 figures, 2 tables, 7 pages of appendices |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.07157 [cs.LG] |
| (or arXiv:2605.07157v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.07157 arXiv-issued DOI via DataCite (pending registration) |
From: Lyra Zhornyak [view email]
[v1]
Fri, 8 May 2026 02:43:11 UTC (2,744 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。