Skip to yearly menu bar Skip to main content


Autoregressive Energy Machines

Conor Durkan · Charlie Nash

Pacific Ballroom #116

Keywords: [ Unsupervised Learning ] [ Monte Carlo Methods ] [ Generative Models ] [ Deep Generative Models ]


Neural density estimators are flexible families of parametric models which have seen widespread use in unsupervised machine learning in recent years. Maximum-likelihood training typically dictates that these models be constrained to specify an explicit density. However, this limitation can be overcome by instead using a neural network to specify an energy function, or unnormalized density, which can subsequently be normalized to obtain a valid distribution. The challenge with this approach lies in accurately estimating the normalizing constant of the high-dimensional energy function. We propose the Autoregressive Energy Machine, an energy-based model which simultaneously learns an unnormalized density and computes an importance-sampling estimate of the normalizing constant for each conditional in an autoregressive decomposition. The Autoregressive Energy Machine achieves state-of-the-art performance on a suite of density-estimation tasks.

Live content is unavailable. Log in and register to view live content