Wasserstein Iterative Networks for Barycenter Estimation. (arXiv:2201.12245v1 [cs.LG])

Web: http://arxiv.org/abs/2201.12245

Wasserstein barycenters have become popular due to their ability to represent
the average of probability measures in a geometrically meaningful way. In this
paper, we present an algorithm to approximate the Wasserstein-2 barycenters of
continuous measures via a generative model. Previous approaches rely on
regularization (entropic/quadratic) which introduces bias or on input convex
neural networks which are not expressive enough for large-scale tasks. In
contrast, our algorithm does not introduce bias and allows using arbitrary
neural networks. In addition, based …

arxiv networks