Edinburgh Research Explorer

A Deep and Tractable Density Estimator

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Original languageEnglish
Title of host publicationProceedings of The 31st International Conference on Machine Learning
Place of PublicationBeijing, China
PublisherJournal of Machine Learning Research: Workshop and Conference Proceedings
Pages467-475
Number of pages9
Volume32
Publication statusPublished - 2014
Event31st International Conference on International Conference on Machine Learning - Beijing, China
Duration: 21 Jun 201426 Jun 2014
https://icml.cc/2014/

Publication series

NameJournal of Machine Learning Research: Workshop and Conference Proceedings
Volume32
ISSN (Electronic)1938-7228

Conference

Conference31st International Conference on International Conference on Machine Learning
Abbreviated titleICML'14
CountryChina
CityBeijing
Period21/06/1426/06/14
Internet address

Abstract

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.

Event

31st International Conference on International Conference on Machine Learning

21/06/1426/06/14

Beijing, China

Event: Conference

Download statistics

No data available

ID: 17904192