ICLR 2017poster194 citations
Stick-Breaking Variational Autoencoders
Eric Nalisnick, Padhraic Smyth
Abstract
We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric version of the variational autoencoder that has a latent representation with stochastic dimensionality. We experimentally demonstrate that the SB-VAE, and a semi-supervised variant, learn highly discriminative latent representations that often outperform the Gaussian VAE’s.
Deep learningUnsupervised LearningSemi-Supervised Learning
BibTeX
@inproceedings{
nalisnick2017stickbreaking,
title={Stick-Breaking Variational Autoencoders},
author={Eric Nalisnick and Padhraic Smyth},
booktitle={International Conference on Learning Representations},
year={2017},
url={https://openreview.net/forum?id=S1jmAotxg}
}