Properties of Discrete Sliced Wasserstein Losses

arXiv:2307.10352v3 Announce Type: replace-cross
Abstract: The Sliced Wasserstein (SW) distance has become a popular alternative to the Wasserstein distance for comparing probability measures. Widespread applications include image processing, domain adaptation and generative modelling, where it is common to optimise some parameters in order to minimise SW, which serves as a loss function between discrete probability measures (since measures admitting densities are numerically unattainable). All these optimisation problems bear the same sub-problem, which is minimising the Sliced Wasserstein energy. In this …

abstract applications arxiv become cs.lg domain domain adaptation function generative image image processing loss losses math.oc math.pr modelling parameters popular probability processing stat.ml type