Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Takeshi Teshima, Isao Ishikawa, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama

Oral presentation: Orals & Spotlights Track 13: Deep Learning/Theory
on 2020-12-08T18:30:00-08:00 - 2020-12-08T18:45:00-08:00
Poster Session 3 (more posters)
on 2020-12-08T21:00:00-08:00 - 2020-12-08T23:00:00-08:00
GatherTown: Theory ( Town B1 - Spot B3 )
Join GatherTown
Only iff poster is crowded, join Zoom . Authors have to start the Zoom call from their Profile page / Presentation History.
Abstract: Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirable characteristics such as analytic invertibility come at the cost of restricting the functional forms. This poses a question on their representation power: are CF-INNs universal approximators for invertible functions? Without a universality, there could be a well-behaved invertible transformation that the CF-INN can never approximate, hence it would render the model class unreliable. We answer this question by showing a convenient criterion: a CF-INN is universal if its layers contain affine coupling and invertible linear functions as special cases. As its corollary, we can affirmatively resolve a previously unsolved problem: whether normalizing flow models based on affine coupling can be universal distributional approximators. In the course of proving the universality, we prove a general theorem to show the equivalence of the universality for certain diffeomorphism classes, a theoretical insight that is of interest by itself.

Preview Video and Chat

Chat is not available.