A simple equivariant machine learning method for dynamics based on scalars
arXiv:2110.03761
Abstract
Physical systems obey strict symmetry principles. We expect that machine learning methods that intrinsically respect these symmetries should have higher prediction accuracy and better generalization in prediction of physical dynamics. In this work we implement a principled model based on invariant scalars, and release open-source code. We apply this Scalars method to a simple chaotic dynamical system, the springy double pendulum. We show that the Scalars method outperforms state-of-the-art approaches for learning the properties of physical systems with symmetries, both in terms of accuracy and speed. Because the method incorporates the fundamental symmetries, we expect it to generalize to different settings, such as changes in the force laws in the system.
References in corpus (14)
- Group Equivariant Convolutional Networks
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Improving galaxy morphologies for SDSS with Deep Learning
- Equivariant message passing for the prediction of tensorial properties and molecular spectra
- Symmetries and many-body excited states with neural-network quantum states
- Non-Gaussian information from weak lensing data via deep learning
- Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
- General -Equivariant Steerable CNNs
- Hamiltonian Graph Networks with ODE Integrators
- N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
- Scalars are universal: Equivariant machine learning, structured like classical physics
- A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
- Rotation Equivariance and Invariance in Convolutional Neural Networks
- Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds