Machine Learning Symmetry Discovery for Integrable Hamiltonian Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hou, Wanda, Li, Molan, You, Yi-Zhuang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911383229038592
author Hou, Wanda
Li, Molan
You, Yi-Zhuang
author_facet Hou, Wanda
Li, Molan
You, Yi-Zhuang
contents We propose a data-driven Machine-Learning Symmetry Discovery (MLSD) framework for identifying continuous symmetry generators and their Lie-algebraic structure directly from phase-space trajectory data expressed in canonical coordinates. MLSD parameterizes candidate conserved quantities with neural networks and learns antisymmetric structure coefficients by enforcing Poisson-bracket closure, supplemented by a weak independence regularizer. We validate MLSD on two integrable benchmark systems -- the three-dimensional Kepler problem and the three-dimensional isotropic harmonic oscillator -- recovering the expected non-Abelian algebras (respectively $\mathfrak{so}(4)$ and $\mathfrak{su}(3)$) up to basis transformations. This work focuses on integrable benchmark dynamics, where global conserved quantities are well-defined and admit compact representations learnable from canonical-coordinate trajectories. Extending symmetry discovery to mixed or chaotic phase-space regimes is an important direction for future work.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14632
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Machine Learning Symmetry Discovery for Integrable Hamiltonian Dynamics
Hou, Wanda
Li, Molan
You, Yi-Zhuang
Disordered Systems and Neural Networks
Classical Physics
Data Analysis, Statistics and Probability
We propose a data-driven Machine-Learning Symmetry Discovery (MLSD) framework for identifying continuous symmetry generators and their Lie-algebraic structure directly from phase-space trajectory data expressed in canonical coordinates. MLSD parameterizes candidate conserved quantities with neural networks and learns antisymmetric structure coefficients by enforcing Poisson-bracket closure, supplemented by a weak independence regularizer. We validate MLSD on two integrable benchmark systems -- the three-dimensional Kepler problem and the three-dimensional isotropic harmonic oscillator -- recovering the expected non-Abelian algebras (respectively $\mathfrak{so}(4)$ and $\mathfrak{su}(3)$) up to basis transformations. This work focuses on integrable benchmark dynamics, where global conserved quantities are well-defined and admit compact representations learnable from canonical-coordinate trajectories. Extending symmetry discovery to mixed or chaotic phase-space regimes is an important direction for future work.
title Machine Learning Symmetry Discovery for Integrable Hamiltonian Dynamics
topic Disordered Systems and Neural Networks
Classical Physics
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2412.14632