We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential functions. This formulation allows us to train a dual objective comprised only of the scalar potential functions, and removes the burden of explicitly computing normalizing flows during training. After training, the normalizing flow is easily recovered from the potential functions.
Cite
@article{arxiv.2006.06033,
title = {Learning normalizing flows from Entropy-Kantorovich potentials},
author = {Chris Finlay and Augusto Gerolin and Adam M Oberman and Aram-Alexandre Pooladian},
journal= {arXiv preprint arXiv:2006.06033},
year = {2020}
}