Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems

arXiv:2610.04723v1 Announce Type: cross Abstract: This work proposes a latent Lagrangian-based framework for reduced-order modelling of forced nonlinear dynamical systems. In contrast with conventional Lagrangian or Hamiltonian neural networks, our approach learns a set of latent coordinates sufficient to capture the dynamics conjointly with two neural networks for the latent kinetic and latent potential energies, and leverages force supervision to eliminate the need for an ODE solver during training. Consistency of physical laws in the latent space is ensured through the principle of virtual work. Results show that the model effectively learns the subtle dynamics induced by the system's nonlinearity and non-convex potential energy, and generalizes well to unseen forces and initial conditions. These observations confirm the physical relevance of the proposed approach, and its interest for model reduction.

Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks
Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks
MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
Symmetric Hermite quadrature-based balanced truncation for learning linear dynamical systems from derivative data

Source: arXiv cs.LG | 2026-10-06

Related