Poster
in
Workshop: Bayesian Deep Learning
Funnels: Exact maximum likelihood with dimensionality reduction
Samuel Klein · John Raine · Tobias Golling · Slava Voloshynovskiy · Sebastion Pina-Otey
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. This layer can also be used with convolutional and feed forward layers.
Chat is not available.