Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …

Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

With the capability of modeling bidirectional contexts, denoising autoencoding based
pretraining like BERT achieves better performance than pretraining approaches based on …

An Introduction to Variational Autoencoders Page 1 An Introduction to Variational Autoencoders
Page 2 Other titles in Foundations and Trends R in Machine Learning Computational Optimal …

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …

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 …

Unsupervised learning of probabilistic models is a central yet challenging problem in
machine learning. Specifically, designing models with tractable learning, sampling …

Modeling the distribution of natural images is a landmark problem in unsupervised learning.
This task requires an image model that is at once expressive, tractable and scalable. We …

Many domains of science have developed complex simulations to describe phenomena of
interest. While these simulations provide high-fidelity models, they are poorly suited for …

The framework of normalizing flows provides a general strategy for flexible variational
inference of posteriors over latent variables. We propose a new type of normalizing flow …