English

Funnels: Exact maximum likelihood with dimensionality reduction

Machine Learning 2021-12-16 v1 Machine Learning

Abstract

Normalizing flows are diffeomorphic, typically dimension-preserving, models trained using the likelihood of the model. We use the SurVAE framework to construct dimension reducing surjective flows via a new layer, known as the funnel. We demonstrate its efficacy on a variety of datasets, and show it improves upon or matches the performance of existing flows while having a reduced latent space size. The funnel layer can be constructed from a wide range of transformations including restricted convolution and feed forward layers.

Keywords

Cite

@article{arxiv.2112.08069,
  title  = {Funnels: Exact maximum likelihood with dimensionality reduction},
  author = {Samuel Klein and John A. Raine and Sebastian Pina-Otey and Slava Voloshynovskiy and Tobias Golling},
  journal= {arXiv preprint arXiv:2112.08069},
  year   = {2021}
}

Comments

16 pages, 5 figures, 8 tables

R2 v1 2026-06-24T08:18:19.240Z