Wrapped Gaussian Process Regression on Riemannian Manifolds

Abstract

Gaussian process (GP) regression is a powerful tool in non-parametric regression providing uncertainty estimates. However, it is limited to data in vector spaces. In fields such as shape analysis and diffusion tensor imaging, the data often lies on a manifold, making GP regression nonviable, as the resulting predictive distribution does not live in the correct geometric space. We tackle the problem by defining wrapped Gaussian processes (WGPs) on Riemannian manifolds, using the probabilistic setting to generalize GP regression to the context of manifold-valued targets. The method is validated empirically on diffusion weighted imaging (DWI) data, directional data on the sphere and in the Kendall shape space, endorsing WGP regression as an efficient and flexible tool for manifold-valued regression.