A multiscale framework for probability measures in Wasserstein spaces is developed, including a refinement operator preserving geodesic structure and an optimality number for detecting non-geodesic dynamics across scales.
Improved training of Wasserstein gans.Advances in neural information processing systems, 30, 2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multiscaling in Wasserstein Spaces
A multiscale framework for probability measures in Wasserstein spaces is developed, including a refinement operator preserving geodesic structure and an optimality number for detecting non-geodesic dynamics across scales.