RNADE: The real-valued neural autoregressive density-estimator
Abstract
We introduce RNADE, a new model for joint density estimation of real-valued vectors. Our model calculates the density of a datapoint as the product of one-dimensional conditionals modeled using mixture density networks with shared parameters. RNADE learns a distributed representation of the data, while having a tractable expression for the calculation of densities. A tractable likelihood allows direct comparison with other methods and training by standard gradient-based optimizers. We compare the performance of RNADE on several datasets of heterogeneous and perceptual data, finding it outperforms mixture models in all but one case.
Cite
@article{arxiv.1306.0186,
title = {RNADE: The real-valued neural autoregressive density-estimator},
author = {Benigno Uria and Iain Murray and Hugo Larochelle},
journal= {arXiv preprint arXiv:1306.0186},
year = {2014}
}
Comments
12 pages, 3 figures, 3 tables, 2 algorithms. Merges the published paper and supplementary material into one document