CubicSpline Flows
Abstract
A normalizing flow models a complex probability density as an invertible transformation of a simple density. The invertibility means that we can evaluate densities and generate samples from a flow. In practice, autoregressive flowbased models are slow to invert, making either density estimation or sample generation slow. Flows based on coupling transforms are fast for both tasks, but have previously performed less well at density estimation than autoregressive flows. We stack a new coupling transform, based on monotonic cubic splines, with LUdecomposed linear layers. The resulting cubicspline flow retains an exact onepass inverse, can be used to generate highquality images, and closes the gap with autoregressive flows on a suite of densityestimation tasks.
 Publication:

arXiv eprints
 Pub Date:
 June 2019
 arXiv:
 arXiv:1906.02145
 Bibcode:
 2019arXiv190602145D
 Keywords:

 Statistics  Machine Learning;
 Computer Science  Machine Learning
 EPrint:
 Appeared at the 1st Workshop on Invertible Neural Networks and Normalizing Flows at ICML 2019