Masked Autoregressive Flow for Density Estimation

Code

• github.com/gpapamak/maf
  OfficialIn papernone★ 0
• github.com/tensorflow/probability
  tf★ 4,416
• github.com/francois-rozet/zuko
  pytorch★ 452
• github.com/NVIDIA/radtts
  pytorch★ 291
• github.com/CW-Huang/CP-Flow
  pytorch★ 85
• github.com/maho3/ltu-ili
  pytorch★ 76
• github.com/kmzzhang/nbi
  pytorch★ 40
• github.com/e-hulten/real_nvp_2d
  pytorch★ 0
• github.com/zhoudoao-bayes/tf-probability
  tf★ 0
• github.com/ikostrikov/pytorch-flows
  pytorch★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions