Modelling Anisotropic Covariance using Stochastic Development and Sub-Riemannian Frame Bundle Geometry

TL;DR

This paper develops a geometric framework using stochastic development and sub-Riemannian geometry on the frame bundle of manifolds to model anisotropic covariance structures for non-linear data analysis.

Contribution

It introduces a novel geometric approach for modeling anisotropic covariance on manifolds using stochastic processes in the frame bundle, incorporating sub-Riemannian structures and transition densities.

Findings

Provides a geometric interpretation of mean and covariance on manifolds.

Identifies subbundles satisfying Hörmander's condition for smooth densities.

Analyzes small time asymptotics of transition densities.

Abstract

We discuss the geometric foundation behind the use of stochastic processes in the frame bundle of a smooth manifold to build stochastic models with applications in statistical analysis of non-linear data. The transition densities for the projection to the manifold of Brownian motions developed in the frame bundle lead to a family of probability distributions on the manifold. We explain how data mean and covariance can be interpreted as points in the frame bundle or, more precisely, in the bundle of symmetric positive definite 2-tensors analogously to the parameters describing Euclidean normal distributions. We discuss a factorization of the frame bundle projection map through this bundle, the natural sub-Riemannian structure of the frame bundle, the effect of holonomy, and the existence of subbundles where the Hormander condition is satisfied such that the Brownian motions have smooth transition densities. We identify the most probable paths for the underlying Euclidean Brownian motion and discuss small time asymptotics of the transition densities on the manifold. The geometric setup yields an intrinsic approach to the estimation of mean and covariance in non-linear spaces.