Multimarginal Schrödinger Barycenter

Abstract: The Wasserstein barycenter plays a fundamental role in averaging measure-valued data under the framework of optimal transport. However, there are tremendous challenges in computing and estimating the Wasserstein barycenter for high-dimensional distributions. In this paper, we introduce the multimarginal Schr\"{o}dinger barycenter (MSB) based on the entropy regularized multimarginal optimal transport problem that admits general-purpose fast algorithms for computation. By recognizing a proper dual geometry, we derive non-asymptotic rates of convergence for estimating several key MSB quantities from point clouds randomly sampled from the input marginal distributions. Specifically, we show that our obtained sample complexity is statistically optimal for estimating the cost functional, Schr\"{o}dinger coupling and barycenter.