Masked Autoregressive Flow for Density Estimation

NeurIPS 2017  ·  George Papamakarios, Theo Pavlakou, Iain Murray ·

Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow. This type of flow is closely related to Inverse Autoregressive Flow and is a generalization of Real NVP. Masked Autoregressive Flow achieves state-of-the-art performance in a range of general-purpose density estimation tasks.

PDF Abstract NeurIPS 2017 PDF NeurIPS 2017 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Density Estimation BSDS300 MADE MoG Log-likelihood 153.71 # 4
Compare
Density Estimation CIFAR-10 MAF Log-likelihood (nats) 3049 # 1
Compare
Density Estimation CIFAR-10 (Conditional) MAF Log-likelihood 5872 # 1
Compare
Density Estimation MNIST MADE MoG Log-likelihood (nats) -1038.5 # 1
Compare
Density Estimation UCI HEPMASS MADE MoG Log-likelihood -15.15 # 1
Compare
Density Estimation UCI MINIBOONE MADE MoG Log-likelihood -12.27 # 1
Compare
Density Estimation UCI POWER MADE MoG Log-likelihood 0.4 # 5
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy