English

RNADE: The real-valued neural autoregressive density-estimator

Machine Learning 2014-01-10 v2 Machine Learning

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.

Keywords

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

R2 v1 2026-06-22T00:26:31.462Z