Lie Generator Networks for Nonlinear Partial Differential Equations

• URL: http://arxiv.org/abs/2603.29264v2
• Date: Wed, 01 Apr 2026 02:49:26 GMT
• Title: Lie Generator Networks for Nonlinear Partial Differential Equations
• Abstract summary: We introduce Lie Generator Network-Koopman (LGN-KM), a neural operator that lifts nonlinear dynamics into a linear latent space.<n>Because the generator is provably stable, it enables guaranteed long-horizon stability, continuous-time evaluation at arbitrary time, and physics-informed cross-viscosity model transfer.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Linear dynamical systems are fully characterized by their eigenspectra, accessible directly from the generator of the dynamics. For nonlinear systems governed by partial differential equations, no equivalent theory exists. We introduce Lie Generator Network-Koopman (LGN-KM), a neural operator that lifts nonlinear dynamics into a linear latent space and learns the continuous-time Koopman generator ($L_k$) through a decomposition $L_k = S - D_k$, where $S$ is skew-symmetric representing conservative inter-modal coupling, and $D_k$ is a positive-definite diagonal encoding modal dissipation. This architectural decomposition enforces stability and enables interpretability through direct spectral access to the learned dynamics. On two-dimensional Navier--Stokes turbulence, the generator recovers the known dissipation scaling and a complete multi-branch dispersion relation from trajectory data alone with no physics supervision. Independently trained models at different flow regimes recover matched gauge-invariant spectral structure, exposing a gauge freedom in the Koopman lifting. Because the generator is provably stable, it enables guaranteed long-horizon stability, continuous-time evaluation at arbitrary time, and physics-informed cross-viscosity model transfer.

Related papers

• Covariance-Regulated Recursive Koopman Learning for Nonlinear Systems with Uncertain Time-Varying Dynamics [25.933323260176167]
  This paper introduces a Covariance-Regulated Recursive Koopman Learning (CR-RKL) framework with two complementary strategies.<n>CR-RKL achieves numerically stable and accurate online modeling, and when embedded in model predictive control, it maintains reliable tracking performance under uncertain, time-varying dynamics.
  arXiv  Detail & Related papers  (2026-06-13T14:22:24Z)
• Interpretable Physics Extraction from Data for Linear Dynamical Systems using Lie Generator Networks [0.0]
  We introduce Lie Generator Networks (LGN), which learn a structured generator A and compute trajectories directly via matrixiation.<n>By parameterizing A = S - D (skew-symmetric minus positive diagonal), stability and dissipation emerge from the underlying architecture.<n>On a 100-dimensional stable RLC ladder, standard derivative-based least-squares system identification can yield unstable eigenvalues.
  arXiv  Detail & Related papers  (2026-03-28T23:20:33Z)
• Random Dot Product Graphs as Dynamical Systems: Limitations and Opportunities [0.0]
  We investigate the differential equations governing the evolution of a temporal network within Random Dot Product Graphs.<n>We identify three fundamental obstructions: gauge freedom from rotational ambiguity in latent positions, realizability constraints from the manifold structure of the probability matrix, and trajectory recovery artifacts from spectral embedding.<n>We prove an identifiability principle: symmetric dynamics cannot absorb skew-symmetric gauge contamination, so dynamics structure can resolve obstructions.
  arXiv  Detail & Related papers  (2026-03-05T21:56:07Z)
• KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra [65.11254608352982]
  We introduce a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators.<n>By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation.
  arXiv  Detail & Related papers  (2026-02-15T06:32:23Z)
• Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning [52.26396748560348]
  We provide an overview of high dimensional dynamical systems driven by random matrices.<n>We focus on applications to simple models of learning and generalization in machine learning theory.
  arXiv  Detail & Related papers  (2026-01-03T00:12:32Z)
• Renormalizable Spectral-Shell Dynamics as the Origin of Neural Scaling Laws [2.779943773196378]
  We show that deep-network training obeys a simple macroscopic structure despite highly nonlinear optimization dynamics.<n>For mean-squared error loss, the training error evolves as $dot e_t=-M(t)e_t$ with $M(t)=J_(t)J_(t)!*$, a time-dependent self-adjoint operator induced by the network Jacobian.<n>This framework explains neural scaling laws and double descent, and unifies lazy (NTK-like) training and feature learning as two limits of the same spectral-shell
  arXiv  Detail & Related papers  (2025-12-11T08:38:46Z)
• RRAEDy: Adaptive Latent Linearization of Nonlinear Dynamical Systems [2.4662459762262894]
  We introduce RRAEDy, a model for learning low-dimensional dynamics in the latent space.<n>We show that RRAEDy achieves accurate and robust predictions.<n>Our code is open-source and available at https://github.com/JadM133/RRAEDy.
  arXiv  Detail & Related papers  (2025-12-08T13:23:12Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Robust Online Control with Model Misspecification [96.23493624553998]
  We study online control of an unknown nonlinear dynamical system with model misspecification. Our study focuses on robustness, which measures how much deviation from the assumed linear approximation can be tolerated.
  arXiv  Detail & Related papers  (2021-07-16T07:04:35Z)
• Estimating Koopman operators for nonlinear dynamical systems: a nonparametric approach [77.77696851397539]
  The Koopman operator is a mathematical tool that allows for a linear description of non-linear systems. In this paper we capture their core essence as a dual version of the same framework, incorporating them into the Kernel framework. We establish a strong link between kernel methods and Koopman operators, leading to the estimation of the latter through Kernel functions.
  arXiv  Detail & Related papers  (2021-03-25T11:08:26Z)
• Lipschitz Recurrent Neural Networks [100.72827570987992]
  We show that our Lipschitz recurrent unit is more robust with respect to input and parameter perturbations as compared to other continuous-time RNNs. Our experiments demonstrate that the Lipschitz RNN can outperform existing recurrent units on a range of benchmark tasks.
  arXiv  Detail & Related papers  (2020-06-22T08:44:52Z)

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.