Skip to yearly menu bar Skip to main content


Sum-of-Squares Polynomial Flow

Priyank Jaini · Kira A. Selby · Yaoliang Yu

Pacific Ballroom #1

Keywords: [ Unsupervised Learning ] [ Generative Models ] [ Deep Generative Models ]


Triangular map is a recent construct in probability theory that allows one to transform any source probability density function to any target density function. Based on triangular maps, we propose a general framework for high-dimensional density estimation, by specifying one-dimensional transformations (equivalently conditional densities) and appropriate conditioner networks. This framework (a) reveals the commonalities and differences of existing autoregressive and flow based methods, (b) allows a unified understanding of the limitations and representation power of these recent approaches and, (c) motivates us to uncover a new Sum-of-Squares (SOS) flow that is interpretable, universal, and easy to train. We perform several synthetic experiments on various density geometries to demonstrate the benefits (and short-comings) of such transformations. SOS flows achieve competitive results in simulations and several real-world datasets.

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