Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

A Deep and Tractable Density Estimator

About

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.

Benigno Uria, Iain Murray, Hugo Larochelle• 2013

Related benchmarks

TaskDatasetResultRank
Density Estimationbinarized MNIST 28x28 (test)
Test LogL-84.55
44
Density EstimationOcr-letters (test)
Avg Log-Likelihood (nats)-27.22
19
Density EstimationUCI Red wine (test)
Avg Test Log-Likelihood-8.76
18
Density EstimationUCI White wine (test)
Average Test Log-Likelihood-9.67
18
Density EstimationUCI Parkinsons (test)
Avg Test Log-Likelihood-0.9
18
Generative ModelingMNIST Binary (test)
NLL (nats)85.1
13
Density EstimationBSDS300 8x8 pixel patches (test)
Avg Test-Set Log-Likelihood157
10
Density EstimationConnect4 (test)
Avg Log-Likelihood (nats)-11.99
9
Density Estimationdna (test)
Avg Log-Likelihood (nats)-82.31
9
Density EstimationMushrooms (test)
Avg Log-Likelihood (nats)-9.68
9
Showing 10 of 17 rows

Other info

Follow for update