Spread Divergences

David Barber, Mingtian Zhang, Raza Habib, Thomas Bird

Abstract: For distributions $p$ and $q$ with different support, the divergence $\div{p}{q}$ generally will not exist. We define a spread divergence $\sdiv{p}{q}$ on modified $p$ and $q$ and describe sufficient conditions for the existence of such a divergence. We give examples of using a spread divergence to train implicit generative models, including linear models (Principal Components Analysis and Independent Components Analysis) and non-linear models (Deep Generative Networks).

Keywords: Generative Adversarial Network, Divergence

TL;DR: Using noise to define the divergence between distributions with different support.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1811.08968/code)