Neural Autoregressive Flows
Abstract
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify and generalize these approaches, replacing the (conditionally) affine univariate transformations of MAF/IAF with a more general class of invertible univariate transformations expressed as monotonic neural networks. We demonstrate that the proposed neural autoregressive flows (NAF) are universal approximators for continuous probability distributions, and their greater expressivity allows them to better capture multimodal target distributions. Experimentally, NAF yields state-of-the-art performance on a suite of density estimation tasks and outperforms IAF in variational autoencoders trained on binarized MNIST.
Cite
@article{arxiv.1804.00779,
title = {Neural Autoregressive Flows},
author = {Chin-Wei Huang and David Krueger and Alexandre Lacoste and Aaron Courville},
journal= {arXiv preprint arXiv:1804.00779},
year = {2018}
}
Comments
16 pages, 10 figures, 3 tables