Masked Autoregressive Flow for Density Estimation

05/19/2017
by   George Papamakarios, et al.
0

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.

READ FULL TEXT

page 14

page 15

research
04/30/2020

A Triangular Network For Density Estimation

In this paper, triangular networks refer to feedforward neural networks ...
research
12/17/2019

HCNAF: Hyper-Conditioned Neural Autoregressive Flow and its Application for Probabilistic Occupancy Map Forecasting

We introduce Hyper-Conditioned Neural Autoregressive Flow (HCNAF); a pow...
research
04/11/2019

Autoregressive Energy Machines

Neural density estimators are flexible families of parametric models whi...
research
07/10/2020

Variable Skipping for Autoregressive Range Density Estimation

Deep autoregressive models compute point likelihood estimates of individ...
research
01/30/2018

Transformation Autoregressive Networks

The fundamental task of general density estimation has been of keen inte...
research
05/30/2022

Flowification: Everything is a Normalizing Flow

We develop a method that can be used to turn any multi-layer perceptron ...
research
10/27/2017

Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions

Deep autoregressive models have shown state-of-the-art performance in de...

Please sign up or login with your details

Forgot password? Click here to reset