Randomised Wasserstein Barycenter Computation: Resampling with Statistical Guarantees
Authors Heinemann F, Munk A, Zemel Y Journal SIAM Journal on Mathematics of Data Science Citation SIAM Journal on Mathematics of Data Science 2022 4:1, 229-259. Abstract We propose a hybrid resampling method to approximate finitely supported Wasserstein barycenters on large-scale datasets, which can be combined with any exact solver.


