Generalized Normalizing Flows via Markov Chains
arXiv:2111.12506 · doi:10.1017/9781009331012
Abstract
Normalizing flows, diffusion normalizing flows and variational autoencoders are powerful generative models. This chapter provides a unified framework to handle these approaches via Markov chains. We 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 us to couple 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. Our framework establishes a useful mathematical tool to combine the various approaches.
arXiv commentarXiv admin note: text overlap with arXiv:2109.11375
References in corpus (11)
- An Introduction to Variational Autoencoders
- NICE: Non-linear Independent Components Estimation
- Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
- Parseval Proximal Neural Networks
- Stabilizing Invertible Neural Networks Using Mixture Models
- Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
- Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint
- PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
- Wasserstein Patch Prior for Image Superresolution
- Generalized Normalizing Flows via Markov Chains
- WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution