The observable Wasserstein distance is a hierarchy of lower bounds on Wasserstein distance via 1-Lipschitz projections to the line, with an injectivity theorem that recovers the full distance when the order exceeds the metric covering dimension of the support.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Smoothness assumptions on graphical model kernels produce Wasserstein estimation rates determined by local graph structure rather than ambient dimension.
citing papers explorer
-
The Observable Wasserstein Distance
The observable Wasserstein distance is a hierarchy of lower bounds on Wasserstein distance via 1-Lipschitz projections to the line, with an injectivity theorem that recovers the full distance when the order exceeds the metric covering dimension of the support.
-
Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models
Smoothness assumptions on graphical model kernels produce Wasserstein estimation rates determined by local graph structure rather than ambient dimension.