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 non- viable, as the resulting predictive distribution does not live in the correct geometric space. We tackle the problem by defining wrapped Gaussian processes (WGPs) on Rieman- nian manifolds, using the probabilistic setting to general- ize 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.
Cite
Text
Mallasto and Feragen. "Wrapped Gaussian Process Regression on Riemannian Manifolds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00585Markdown
[Mallasto and Feragen. "Wrapped Gaussian Process Regression on Riemannian Manifolds." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/mallasto2018cvpr-wrapped/) doi:10.1109/CVPR.2018.00585BibTeX
@inproceedings{mallasto2018cvpr-wrapped,
title = {{Wrapped Gaussian Process Regression on Riemannian Manifolds}},
author = {Mallasto, Anton and Feragen, Aasa},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00585},
url = {https://mlanthology.org/cvpr/2018/mallasto2018cvpr-wrapped/}
}