Timezone: »

 
Poster
The continuous Bernoulli: fixing a pervasive error in variational autoencoders
Gabriel Loaiza-Ganem · John Cunningham

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #187
in Probabilistic Methods -- Latent Variable Models »

Variational autoencoders (VAE) have quickly become a central tool in machine learning, applicable to a broad range of data types and latent variable models. By far the most common first step, taken by seminal papers and by core software libraries alike, is to model MNIST data using a deep network parameterizing a Bernoulli likelihood. This practice contains what appears to be and what is often set aside as a minor inconvenience: the pixel data is [0,1] valued, not {0,1} as supported by the Bernoulli likelihood. Here we show that, far from being a triviality or nuisance that is convenient to ignore, this error has profound importance to VAE, both qualitative and quantitative. We introduce and fully characterize a new [0,1]-supported, single parameter distribution: the continuous Bernoulli, which patches this pervasive bug in VAE. This distribution is not nitpicking; it produces meaningful performance improvements across a range of metrics and datasets, including sharper image samples, and suggests a broader class of performant VAE.

Keywords: Probabilistic Methods · Algorithms -> Unsupervised Learning; Deep Learning -> Deep Autoencoders; Deep Learning · Generative Models; Probabilistic Meth
[ Paper]  [ Poster] 

Author Information

Gabriel Loaiza-Ganem (Layer 6 AI)
John Cunningham (University of Columbia)

More from the Same Authors