Provably convergent stochastic fixed-point algorithm for free-support Wasserstein barycenter of continuous non-parametric measures

Abstract

We develop an estimator-based stochastic fixed-point framework for approximately computing the 2-Wasserstein barycenter of continuous, non-parametric probability measures. Notably, we provide the first rigorous convergence analysis for an implementable estimator-based stochastic extension of the fixed-point iterative scheme proposed by Álvarez-Esteban, del Barrio, Cuesta-Albertos, and Matrán (2016). In particular, we establish almost sure convergence and identify sufficient conditions under which the proposed scheme achieves a geometric convergence rate in the number of iterations, provided that the errors in the approximation steps are suitably controlled. We subsequently propose a concrete, provably convergent, and computationally tractable stochastic algorithm that accommodates input measures satisfying Caffarelli-type regularity conditions, which form a dense subset of the Wasserstein space. This algorithm leverages a modified entropic optimal transport map estimator to enable efficient and scalable implementation. To facilitate quantitative evaluation, we further propose a novel and efficient procedure for synthetically generating benchmark instances, in which the input measures exhibit non-trivial features and the corresponding barycenters are approximately known. Numerical experiments on both synthetic and real-world datasets demonstrate the strong computational efficiency, estimation accuracy, and sampling flexibility of our approach.