Work

Funnels: Exact maximum likelihood with dimensionality reduction

Year: 2021

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2112.08069

Authors: Klein, Samuel, Raine, John A., Pina-Otey, Sebastian, Voloshynovskiy, Slava, Golling, Tobias

Institution: University of Geneva

Language: English

Topic: Gaussian Processes and Bayesian Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Award: Robust Deep Density Models for High-Energy Particle Physics and Solar Flare Analysis (RODEM)

OpenAlex ID: W4226270937

Cites:

Cited by: 2

Related to: 10