Manifold Density Estimation via Generalized Dequantization

Abstract

Density estimation is an important technique for characterizing distributions given observations. Much existing research on density estimation has focused on cases wherein the data lies in a Euclidean space. However, some kinds of data are not well-modeled by supposing that their underlying geometry is Euclidean. Instead, it can be useful to model such data as lying on a {\it manifold} with some known structure. For instance, some kinds of data may be known to lie on the surface of a sphere. We study the problem of estimating densities on manifolds. We propose a method, inspired by the literature on "dequantization," which we interpret through the lens of a coordinate transformation of an ambient Euclidean space and a smooth manifold of interest. Using methods from normalizing flows, we apply this method to the dequantization of smooth manifold structures in order to model densities on the sphere, tori, and the orthogonal group.

arXiv commentAdditional experiments and theory

References in corpus (7)

• Normalizing Flows: An Introduction and Review of Current Methods
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• Normalizing Flows on Tori and Spheres
• Sum-of-Squares Polynomial Flow
• Neural Manifold Ordinary Differential Equations
• Learning Discrete Distributions by Dequantization
• Categorical Normalizing Flows via Continuous Transformations