Dynamical and Optimization Trade-offs of Levi--Civita Coordinates for Learned Close-Encounter Dynamics
Abhishek Shankar
physics.comp-ph, astro-ph.EP, cs.LG
Submitted: 2026-07-22
Comments: 16 pages, 4 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Hamiltonian Graph Networks with ODE Integrators
- SympNets: Intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
- Time-adaptive H'enonNets for separable Hamiltonian systems
- Nonseparable Symplectic Neural Networks
- Unifying physical systems' inductive biases in neural ODE using dynamics constraints
- Deep Learning Based Dynamics Identification and Linearization of Orbital Problems using Koopman Theory
- Neural Network Perturbation Theory (NNPT): Learning Residual Corrections from Exact Solutions
- ATLAS-NN: Adaptive Transfer Learnable Symplectic-aware Neural Network for Long-Time Hamiltonian Dynamics
Related papers
- Learning Spectral-Like Mesh-Free Discretisations
- Breaking the Exascale Barrier for the Electronic Structure Problem in Ab-Initio Molecular Dynamics
- Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations
- Metal-Insulator Transition of Solid Hydrogen by the Antisymmetric Shadow Wave Function
- Resonating Valence Bond Quantum Monte Carlo: Application to the ozone molecule
- Quantifying Gibbs measures of disordered crystals up to the solid-liquid phase transition