Variational Autoencoders and Nonlinear ICA: A Unifying Framework

by   Ilyes Khemakhem, et al.

The framework of variational autoencoders allows us to efficiently learn deep latent-variable models, such that the model's marginal distribution over observed variables fits the data. Often, we're interested in going a step further, and want to approximate the true joint distribution over observed and latent variables, including the true prior and posterior distributions over latent variables. This is known to be generally impossible due to unidentifiability of the model. We address this issue by showing that for a broad family of deep latent-variable models, identification of the true joint distribution over observed and latent variables is actually possible up to a simple transformation, thus achieving a principled and powerful form of disentanglement. Our result requires a factorized prior distribution over the latent variables that is conditioned on an additionally observed variable, such as a class label or almost any other observation. We build on recent developments in nonlinear ICA, which we extend to the case with noisy, undercomplete or discrete observations, integrated in a maximum likelihood framework. The result also trivially contains identifiable flow-based generative models as a special case.


page 1

page 2

page 3

page 4


Avoiding Latent Variable Collapse With Generative Skip Models

Variational autoencoders (VAEs) learn distributions of high-dimensional ...

Learning Exponential Family Graphical Models with Latent Variables using Regularized Conditional Likelihood

Fitting a graphical model to a collection of random variables given samp...

Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)

A central question of representation learning asks under which condition...

Amortised Learning by Wake-Sleep

Models that employ latent variables to capture structure in observed dat...

Recursive nonlinear-system identification using latent variables

In this paper we develop a method for learning nonlinear systems with mu...

Detecting Hierarchical Changes in Latent Variable Models

This paper addresses the issue of detecting hierarchical changes in late...

Towards Robust Unsupervised Disentanglement of Sequential Data – A Case Study Using Music Audio

Disentangled sequential autoencoders (DSAEs) represent a class of probab...