Normalizing Flows: An Introduction and Review of Current Methods

TL;DR

This paper provides a comprehensive review of Normalizing Flows, a class of generative models that enable efficient sampling and exact density evaluation, highlighting current methods, challenges, and future research directions.

Contribution

It offers a detailed overview of existing Normalizing Flow techniques, clarifies their theoretical foundations, and discusses open questions and future research opportunities.

Findings

Normalizing Flows enable efficient sampling and exact density computation.

Current methods vary in architecture and training strategies.

Open questions include scalability and model expressiveness.

Abstract

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.