Density estimation using Real NVP
This addresses the challenge of designing tractable probabilistic models for machine learning, offering a novel approach with broad applications in unsupervised learning.
The paper tackled the problem of unsupervised learning of probabilistic models by introducing real NVP transformations, which enable exact log-likelihood computation, sampling, and inference, and demonstrated its effectiveness on natural image datasets.
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.