Density estimation using Real NVP

27 May 2016  ·  Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio ·

Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation and latent variable manipulations.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation CIFAR-10 Real NVP bits/dimension 3.5 # 61
Image Generation CIFAR-10 Real NVP (Dinh et al., 2017) bits/dimension 3.49 # 60
Image Generation ImageNet 32x32 Real NVP (Dinh et al., 2017) bpd 4.28 # 22

Methods