Variational Mixture of Normalizing Flows

by   Guilherme G. P. Freitas Pires, et al.

In the past few years, deep generative models, such as generative adversarial networks GAN, variational autoencoders vaepaper, and their variants, have seen wide adoption for the task of modelling complex data distributions. In spite of the outstanding sample quality achieved by those early methods, they model the target distributions implicitly, in the sense that the probability density functions induced by them are not explicitly accessible. This fact renders those methods unfit for tasks that require, for example, scoring new instances of data with the learned distributions. Normalizing flows have overcome this limitation by leveraging the change-of-variables formula for probability density functions, and by using transformations designed to have tractable and cheaply computable Jacobians. Although flexible, this framework lacked (until recently semisuplearning_nflows, RAD) a way to introduce discrete structure (such as the one found in mixtures) in the models it allows to construct, in an unsupervised scenario. The present work overcomes this by using normalizing flows as components in a mixture model and devising an end-to-end training procedure for such a model. This procedure is based on variational inference, and uses a variational posterior parameterized by a neural network. As will become clear, this model naturally lends itself to (multimodal) density estimation, semi-supervised learning, and clustering. The proposed model is illustrated on two synthetic datasets, as well as on a real-world dataset. Keywords: Deep generative models, normalizing flows, variational inference, probabilistic modelling, mixture models.


page 5

page 11

page 13


Meta-Amortized Variational Inference and Learning

How can we learn to do probabilistic inference in a way that generalizes...

A Factorial Mixture Prior for Compositional Deep Generative Models

We assume that a high-dimensional datum, like an image, is a composition...

Continuous-Time Flows for Deep Generative Models

Normalizing flows have been developed recently as a method for drawing s...

Discretely Indexed Flows

In this paper we propose Discretely Indexed flows (DIF) as a new tool fo...

Variational Inference using Implicit Distributions

Generative adversarial networks (GANs) have given us a great tool to fit...

Gradient Boosted Flows

Normalizing flows (NF) are a powerful framework for approximating poster...

Inducing Interpretable Representations with Variational Autoencoders

We develop a framework for incorporating structured graphical models in ...