The authors formulate geodesic PCA in Wasserstein space through Otto's fiber bundle, solve it exactly for Gaussians, and approximate it for general measures with neural geodesic parameterizations.
Gradient flows: in metric spaces and in the space of probability measures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
On the Wasserstein Geodesic Principal Component Analysis of probability measures
The authors formulate geodesic PCA in Wasserstein space through Otto's fiber bundle, solve it exactly for Gaussians, and approximate it for general measures with neural geodesic parameterizations.