Calculus of Variations and Geometric Measure Theory
home | mail | papers | authors | news | seminars | events | open positions | login

C. Finlay - A. Gerolin - Adam M Oberman - A. A. Pooladian

Learning normalizing flows from Entropy-Kantorovich potentials

created by gerolin on 23 Jun 2020

[BibTeX]

preprint

Inserted: 23 jun 2020

Year: 2020

ArXiv: 2006.06033 PDF

Abstract:

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.

Credits | Cookie policy | HTML 5 | CSS 2.1