A RAD approach to deep mixture models

03/18/2019
by   Laurent Dinh, et al.
4

Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for modeling and representing discrete structures in data distributions, for example class membership or discrete symmetries. To address this difficulty, we present a normalizing flow architecture which relies on domain partitioning using locally invertible functions, and possesses both real and discrete valued latent variables. This Real and Discrete (RAD) approach retains the desirable normalizing flow properties of exact sampling, exact inference, and analytically computable probabilities, while at the same time allowing simultaneous modeling of both continuous and discrete structure in a data distribution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/01/2021

GraphDF: A Discrete Flow Model for Molecular Graph Generation

We consider the problem of molecular graph generation using deep models....
research
06/28/2020

Mixture of Discrete Normalizing Flows for Variational Inference

Advances in gradient-based inference have made distributional approximat...
research
05/26/2021

Augmented KRnet for density estimation and approximation

In this work, we have proposed augmented KRnets including both discrete ...
research
07/24/2021

Discrete Denoising Flows

Discrete flow-based models are a recently proposed class of generative m...
research
12/24/2020

RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces

Efficient sampling of complex data distributions can be achieved using t...
research
05/23/2019

Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

We address the problem of unsupervised disentanglement of discrete and c...
research
09/18/2019

Scalable Deep Unsupervised Clustering with Concrete GMVAEs

Discrete random variables are natural components of probabilistic cluste...

Please sign up or login with your details

Forgot password? Click here to reset