Learnable Explicit Density for Continuous Latent Space and Variational Inference
Abstract
In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the learning of VAEs into layerwise density estimation, and argue that having a flexible prior is beneficial to both sample generation and inference. Second, we analyze the family of inverse autoregressive flows (inverse AF) and show that with further improvement, inverse AF could be used as universal approximation to any complicated posterior. Our analysis results in a unified approach to parameterizing a VAE, without the need to restrict ourselves to use factorial Gaussians in the latent real space.
Keywords
Cite
@article{arxiv.1710.02248,
title = {Learnable Explicit Density for Continuous Latent Space and Variational Inference},
author = {Chin-Wei Huang and Ahmed Touati and Laurent Dinh and Michal Drozdzal and Mohammad Havaei and Laurent Charlin and Aaron Courville},
journal= {arXiv preprint arXiv:1710.02248},
year = {2017}
}
Comments
2 figures, 5 pages, submitted to ICML Principled Approaches to Deep Learning workshop