keyword

radial flows

Radial flows are a family of invertible and differentiable transformations used in normalizing flows that modify probability distributions by expanding or contracting space radially around a specific reference point. In probabilistic modeling and machine learning, these transformations shift points toward or away from a parameterized center, allowing simple base distributions to be warped into more expressive and flexible target distributions. A key characteristic of radial flows is that the determinant of their Jacobian matrix can be computed in linear time with respect to the input dimensionality, providing a computationally efficient mechanism for exact density evaluation and sampling in tasks such as variational inference.

1 item

Normalizing Flows: An Introduction and Review of Current Methods

Ivan Kobyzev, Simon J.D. Prince, Marcus A. Brubaker

OrganizationsBorealis AIYork University

Why you should read this

Explains the mathematical foundations and architectural design principles of normalizing flows, offering a clear guide to how these models achieve exact probability density estimation and efficient sampling.

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.

Source

https://arxiv.org/pdf/1908.09257

Added

2026-09-24