
Generalized Normalizing Flows via Markov Chains
Cambridge University Press
Published on 2. February 2023
Book
Paperback/Softback
66 pages
978-1-009-33100-5 (ISBN)
Description
Normalizing flows, diffusion normalizing flows and variational autoencoders are powerful generative models. This Element provides a unified framework to handle these approaches via Markov chains. The authors consider stochastic normalizing flows as a pair of Markov chains fulfilling some properties, and show how many state-of-the-art models for data generation fit into this framework. Indeed numerical simulations show that including stochastic layers improves the expressivity of the network and allows for generating multimodal distributions from unimodal ones. The Markov chains point of view enables the coupling of both deterministic layers as invertible neural networks and stochastic layers as Metropolis-Hasting layers, Langevin layers, variational autoencoders and diffusion normalizing flows in a mathematically sound way. The authors' framework establishes a useful mathematical tool to combine the various approaches.
More details
Series
Language
English
Place of publication
Cambridge
United Kingdom
Product notice
Paperback (trade)
Illustrations
Worked examples or Exercises
Dimensions
Height: 229 mm
Width: 152 mm
Thickness: 4 mm
Weight
100 gr
ISBN-13
978-1-009-33100-5 (9781009331005)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Classification
Other editions
Additional editions

Paul Lyonel Hagemann | Johannes Hertrich | Gabriele Steidl
Generalized Normalizing Flows via Markov Chains
E-Book
01/2023
Cambridge University Press
€22.49
Available for download

Paul Lyonel Hagemann | Johannes Hertrich | Gabriele Steidl
Generalized Normalizing Flows via Markov Chains
E-Book
01/2023
Cambridge University Press
€22.49
Available for download
Persons
Author
Technische Universitaet Berlin
Technische Universitaet Berlin
Technische Universitaet Berlin
Content
1. Introduction; 2. Preliminaries; 3. Normalizing Flows; 4. Stochastic Normalizing Flows; 5. Stochastic Layers; 6. Conditional Generative Modeling; 7. Numerical Results; 8. Conclusions and Open Questions; References.