Transformation Autoregressive Networks

Junier Oliva, Avinava Dubey, Barnabás Póczos, Eric P. Xing, Jeff Schneider

Abstract: The fundamental task of general density estimation has been of keen interest to machine learning. Recent advances in density estimation have either: a) proposed using a flexible model to estimate the conditional factors of the chain rule; or b) used flexible, non-linear transformations of variables of a simple base distribution. Instead, this work jointly leverages transformations of variables and autoregressive conditional models, and proposes novel methods for both. We provide a deeper understanding of our models, showing a considerable improvement with our methods through a comprehensive study over both real world and synthetic data. Moreover, we illustrate the use of our models in outlier detection and image modeling task.

Keywords: density estimation, autoregressive models, RNNs

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1801.09819/code)