Timezone: »

 
Poster
A New Distribution on the Simplex with Auto-Encoding Applications
Andrew Stirn · Tony Jebara · David Knowles

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #184
in Probabilistic Methods -- Variational Inference »

We construct a new distribution for the simplex using the Kumaraswamy distribution and an ordered stick-breaking process. We explore and develop the theoretical properties of this new distribution and prove that it exhibits symmetry (exchangeability) under the same conditions as the well-known Dirichlet. Like the Dirichlet, the new distribution is adept at capturing sparsity but, unlike the Dirichlet, has an exact and closed form reparameterization--making it well suited for deep variational Bayesian modeling. We demonstrate the distribution's utility in a variety of semi-supervised auto-encoding tasks. In all cases, the resulting models achieve competitive performance commensurate with their simplicity, use of explicit probability models, and abstinence from adversarial training.

Keywords: Variational Inference · Generative Models · Probabilistic Methods · Algorithms -> Semi-Supervised Learning; Deep Learning -> Deep Autoencoders; Deep Learning
[ Paper]  [ Poster] 

Author Information

Andrew Stirn (Columbia University)
Tony Jebara (Spotify)
David Knowles (Columbia University)

More from the Same Authors