30 citations · 85 across the 7 of their papers we have counts for
Showing 2018Show all
3 papers · 1 filter
stat.ML2018
Resampled Priors for Variational Autoencoders
Matthias Bauer, Andriy Mnih
We propose Learned Accept/Reject Sampling (LARS), a method for constructing richer priors using rejection sampling with a learned acceptance function. This work is motivated by rec…
cs.LG2018
Implicit Reparameterization Gradients
Michael Figurnov, Shakir Mohamed, Andriy Mnih
By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for trai…
stat.ML2018
Disentangling by Factorising
Hyunjik Kim, Andriy Mnih
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method t…