Generalized Normalizing Flows via Markov Chains (Paperback)

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.

General

Imprint:	Cambridge UniversityPress
Country of origin:	United Kingdom
Series:	Elements in Non-local Data Interactions: Foundations and Applications
Release date:	2023
Authors:	Paul Lyonel Hagemann • Johannes Hertrich • Gabriele Steidl
Format:	Paperback - Trade
Pages:	75
ISBN-13:	978-1-00-933100-5
Categories:	Books > Science & Mathematics > Mathematics > Applied mathematics > Stochastics Promotions
LSN:	1-00-933100-0
Barcode:	9781009331005

Is the information for this product incomplete, wrong or inappropriate? Let us know about it.

Does this product have an incorrect or missing image? Send us a new image.

Is this product missing categories? Add more categories.

Review This Product

No reviews yet - be the first to create one!