Normalizing Flows on Riemannian Manifolds

11/07/2016
by   Mevlana C. Gemici, et al.
Google
0

We consider the problem of density estimation on Riemannian manifolds. Density estimation on manifolds has many applications in fluid-mechanics, optics and plasma physics and it appears often when dealing with angular variables (such as used in protein folding, robot limbs, gene-expression) and in general directional statistics. In spite of the multitude of algorithms available for density estimation in the Euclidean spaces R^n that scale to large n (e.g. normalizing flows, kernel methods and variational approximations), most of these methods are not immediately suitable for density estimation in more general Riemannian manifolds. We revisit techniques related to homeomorphisms from differential geometry for projecting densities to sub-manifolds and use it to generalize the idea of normalizing flows to more general Riemannian manifolds. The resulting algorithm is scalable, simple to implement and suitable for use with automatic differentiation. We demonstrate concrete examples of this method on the n-sphere S^n.

READ FULL TEXT VIEW PDF

Authors

page 1

page 2

page 3

07/13/2020

Strong Uniform Consistency with Rates for Kernel Density Estimators with General Kernels on Manifolds

We provide a strong uniform consistency result with the convergence rate...
02/14/2021

Manifold Density Estimation via Generalized Dequantization

Density estimation is an important technique for characterizing distribu...
10/04/2021

Implicit Riemannian Concave Potential Maps

We are interested in the challenging problem of modelling densities on R...
06/18/2020

Riemannian Continuous Normalizing Flows

Normalizing flows have shown great promise for modelling flexible probab...
09/12/2019

Gaussians on Riemannian Manifolds for Robot Learning and Adaptive Control

This paper presents an overview of robot learning and adaptive control a...
08/18/2021

Moser Flow: Divergence-based Generative Modeling on Manifolds

We are interested in learning generative models for complex geometries d...
05/26/2021

Simulation of Conditioned Semimartingales on Riemannian Manifolds

We present a scheme for simulating conditioned semimartingales taking va...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

References