Equivariant Hamiltonian Flows
Machine Learning
2019-10-01 v1 Machine Learning
Abstract
This paper introduces equivariant hamiltonian flows, a method for learning expressive densities that are invariant with respect to a known Lie-algebra of local symmetry transformations while providing an equivariant representation of the data. We provide proof of principle demonstrations of how such flows can be learnt, as well as how the addition of symmetry invariance constraints can improve data efficiency and generalisation. Finally, we make connections to disentangled representation learning and show how this work relates to a recently proposed definition.
Cite
@article{arxiv.1909.13739,
title = {Equivariant Hamiltonian Flows},
author = {Danilo Jimenez Rezende and Sébastien Racanière and Irina Higgins and Peter Toth},
journal= {arXiv preprint arXiv:1909.13739},
year = {2019}
}