Equivariant Manifold Flows. (arXiv:2107.08596v2 [stat.ML] UPDATED)

Web: http://arxiv.org/abs/2107.08596

Tractably modelling distributions over manifolds has long been an important
goal in the natural sciences. Recent work has focused on developing general
machine learning models to learn such distributions. However, for many
applications these distributions must respect manifold symmetries -- a trait
which most previous models disregard. In this paper, we lay the theoretical
foundations for learning symmetry-invariant distributions on arbitrary
manifolds via equivariant manifold flows. We demonstrate the utility of our
approach by using it to learn gauge invariant …

arxiv manifold ml