Wasserstein gradient flow for optimal probability measure decomposition

TL;DR

This work analytically explores the structures of the support of optimal sub-measures and introduces algorithms based on Wasserstein gradient flow, demonstrating their convergence.

Abstract

We examine the infinite-dimensional optimization problem of finding a decomposition of a probability measure into K probability sub-measures to minimize specific loss functions inspired by applications in clustering and user grouping. We analytically explore the structures of the support of optimal sub-measures and introduce algorithms based on Wasserstein gradient flow, demonstrating their convergence. Numerical results illustrate the implementability of our algorithms and provide further insights.