Normalizing Flows: An Introduction and Review of Current Methods

Ivan Kobyzev; Simon J. D. Prince; Marcus A. Brubaker

doi:10.1109/tpami.2020.2992934

Abstract

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.

Keywords

Current (fluid)Computer scienceContext (archaeology)Generative grammarSampling (signal processing)Artificial intelligenceMachine learningData scienceGeographyEngineering

Affiliated Institutions

Collège Boréal CA

Related Publications

Diffusion Models in Vision: A Survey

Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu +1 more

Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep...

2023 IEEE Transactions on Pattern Analysis... 1234 citations

Machine Learning Interpretability: A Survey on Methods and Metrics

Diogo V. Carvalho , Eduardo M. Pereira , Jaime S. Cardoso

Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning th...

2019 Electronics 1600 citations

Generative adversarial networks

Ian Goodfellow , Jean Pouget-Abadie , Mehdi Mirza +5 more

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a c...

2020 Communications of the ACM 11829 citations

Extracting and composing robust features with denoising autoencoders

Pascal Vincent , Hugo Larochelle , Yoshua Bengio +1 more

Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to u...

2008 7123 citations

Generative Adversarial Networks: An Overview

Antonia Creswell , Tom White , Vincent Dumoulin +3 more

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this by deriving backpropagation sig...

2018 IEEE Signal Processing Magazine 4073 citations

Publication Info

Year: 2020
Type: article
Volume: 43
Issue: 11
Pages: 3964-3979
Citations: 1092
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Normalizing Flows: An Introduction and Review of Current Methods

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1092

OpenAlex

Cite This

APA Style

                            
                                    Ivan Kobyzev, 
                                
                                    Simon J. D. Prince, 
                                
                                    Marcus A. Brubaker
                                
                            (2020). 
                            Normalizing Flows: An Introduction and Review of Current Methods. 
                            IEEE Transactions on Pattern Analysis and Machine Intelligence
                            , 43
                            (11)
                            , 3964-3979.
                            https://doi.org/10.1109/tpami.2020.2992934

Identifiers

DOI: 10.1109/tpami.2020.2992934