A Deep and Tractable Density Estimator

Benigno Uría, Iain Murray, and Hugo Larochelle.

The Neural Autoregressive Distribution Estimator (NADE) and its real-valued version RNADE are competitive density models of multidimensional data across a variety of domains. These models use a fixed, arbitrary ordering of the data dimensions. One can easily condition on variables at the beginning of the ordering, and marginalize out variables at the end of the ordering, however other inference tasks require approximate inference. In this work we introduce an efficient procedure to simultaneously train a NADE model for each possible ordering of the variables, by sharing parameters across all these models. We can thus use the most convenient model for each inference task at hand, and ensembles of such models with different orderings are immediately available. Moreover, unlike the original NADE, our training procedure scales to deep models. Empirically, ensembles of Deep NADE models obtain state of the art density estimation performance.

Proceedings of the 31st International Conference on Machine Learning, JMLR W&CP 32(1):467–475, 2014.
[PDF, DjVu, GoogleViewer, arXiv, BibTeX]

See also: the earlier papers on NADE and RNADE.

Google magenta's Coconet (arXiv, blog) builds on the ideas in this paper, and was used to make a Bach harmonization doodle.