Localised Generative Flows

Rob Cornish, Anthony Caterini, George Deligiannidis, Arnaud Doucet

TL;DR: We use a deep continuous mixture of bijections to improve normalising flows for density estimation.

Abstract: We argue that flow-based density models based on continuous bijections are limited in their ability to learn target distributions with complicated topologies, and propose localised generative flows (LGFs) to address this problem. LGFs are composed of stacked continuous mixtures of bijections, which enables each bijection to learn a local region of the target rather than its entirety. Our method is a generalisation of existing flow-based methods, which can be used without modification as the basis for an LGF model. Unlike normalising flows, LGFs do not permit exact computation of log likelihoods, but we propose a simple variational scheme that performs well in practice. We show empirically that LGFs yield improved performance across a variety of common density estimation tasks.

Code: https://github.com/anonsubmission974/lgf

Keywords: Deep generative models, normalizing flows, variational inference

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:1909.13833/code)