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.

TL;DR: We define a variational autoencoder variant with stick-breaking latent variables thereby giving it adaptive width.

Conflicts: uci.edu, lehigh.edu, twitter.com

Keywords: Deep learning, Unsupervised Learning, Semi-Supervised Learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1605.06197/code)