Normalizing Flows for Probabilistic Modeling and Inference
It provides a comprehensive overview for researchers in machine learning and statistics, but is incremental as it synthesizes existing work rather than introducing new methods.
This review tackles the need for a unified perspective on normalizing flows, a mechanism for defining expressive probability distributions, by describing them through the lens of probabilistic modeling and inference, covering principles, expressive power, and applications like generative modeling and approximate inference.
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.