New class of CDF-based estimators for sliced Wasserstein distance avoids sorting, enables massive parallelism, and suits federated learning and Gaussian mixture models.
One-dimensional empirical measures, order statistics, and
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions
New class of CDF-based estimators for sliced Wasserstein distance avoids sorting, enables massive parallelism, and suits federated learning and Gaussian mixture models.