Learning from Uncertain Curves: The 2-Wasserstein Metric for Gaussian Processes

Abstract

We introduce a novel framework for statistical analysis of populations of non-degenerate Gaussian processes (GPs), which are natural representations of uncertain curves. This allows inherent variation or uncertainty in function-valued data to be properly incorporated in the population analysis. Using the 2-Wasserstein metric we geometrize the space of GPs with L2 mean and covariance functions over compact index spaces. We prove uniqueness of the barycenter of a population of GPs, as well as convergence of the metric and the barycenter of their finite-dimensional counterparts. This justifies practical computations. Finally, we demonstrate our framework through experimental validation on GP datasets representing brain connectivity and climate development. A Matlab library for relevant computations will be published at https://sites.google.com/view/antonmallasto/software.

Cite

Text

Mallasto and Feragen. "Learning from Uncertain Curves: The 2-Wasserstein Metric for Gaussian Processes." Neural Information Processing Systems, 2017.

Markdown

[Mallasto and Feragen. "Learning from Uncertain Curves: The 2-Wasserstein Metric for Gaussian Processes." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/mallasto2017neurips-learning/)

BibTeX

@inproceedings{mallasto2017neurips-learning,
  title     = {{Learning from Uncertain Curves: The 2-Wasserstein Metric for Gaussian Processes}},
  author    = {Mallasto, Anton and Feragen, Aasa},
  booktitle = {Neural Information Processing Systems},
  year      = {2017},
  pages     = {5660-5670},
  url       = {https://mlanthology.org/neurips/2017/mallasto2017neurips-learning/}
}