Normalizing flows (NF) recently gained attention as a way to construct generative networks with exact likelihood calculation out of composable layers. However, NF is restricted to dimension-preserving transformations. Surjection VAE (SurVAE) has been proposed to extend NF to dimension-altering transformations. Such networks are desirable because they are expressive and can be precisely trained. We show that the approaches are a re-invention of PDF projection, which appeared over twenty years earlier and is much further developed.
Cite
@article{arxiv.2311.14412,
title = {A Comparison of PDF Projection with Normalizing Flows and SurVAE},
author = {Paul M. Baggenstoss and Felix Govaers},
journal= {arXiv preprint arXiv:2311.14412},
year = {2023}
}