English

AI Poincar\'{e} 2.0: Machine Learning Conservation Laws from Differential Equations

Machine Learning 2022-11-01 v2 Earth and Planetary Astrophysics Exactly Solvable and Integrable Systems Classical Physics Fluid Dynamics

Abstract

We present a machine learning algorithm that discovers conservation laws from differential equations, both numerically (parametrized as neural networks) and symbolically, ensuring their functional independence (a non-linear generalization of linear independence). Our independence module can be viewed as a nonlinear generalization of singular value decomposition. Our method can readily handle inductive biases for conservation laws. We validate it with examples including the 3-body problem, the KdV equation and nonlinear Schr\"odinger equation.

Cite

@article{arxiv.2203.12610,
  title  = {AI Poincar\'{e} 2.0: Machine Learning Conservation Laws from Differential Equations},
  author = {Ziming Liu and Varun Madhavan and Max Tegmark},
  journal= {arXiv preprint arXiv:2203.12610},
  year   = {2022}
}

Comments

15 pages, 12 figures

R2 v1 2026-06-24T10:23:46.088Z