Equivariant Hamiltonian Flows

NeurIPS 2019

Equivariant Hamiltonian Flows

Dec 15, 2019
|
39 views
|
Details
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. Speakers: Danilo Jimenez Rezende

Comments
loading...