Stochastic Gradient Descent for Barycenters in Wasserstein Space
Abstract
We present and study a novel algorithm for the computation of 2-Wasserstein population barycenters of absolutely continuous probability measures on Euclidean space. The proposed method can be seen as a stochastic gradient descent procedure in the 2-Wasserstein space, as well as a manifestation of a Law of Large Numbers therein. The algorithm aims at finding a Karcher mean or critical point in this setting, and can be implemented ``online", sequentially using i.i.d. random measures sampled from the population law. We provide natural sufficient conditions for this algorithm to a.s. converge in the Wasserstein space towards the population barycenter, and we introduce a novel, general condition which ensures uniqueness of Karcher means and moreover allows us to obtain explicit, parametric convergence rates for the expected optimality gap. We furthermore study the mini-batch version of this algorithm, and discuss examples of families of population laws to which our method and results can be applied. This work expands and deepens ideas and results introduced in an early version of \cite{backhoff2018bayesian}, in which a statistical application (and numerical implementation) of this method is developed in the context of Bayesian learning.
Cite
@article{arxiv.2201.04232,
title = {Stochastic Gradient Descent for Barycenters in Wasserstein Space},
author = {Julio Backhoff-Veraguas and Joaquin Fontbona and Gonzalo Rios and Felipe Tobar},
journal= {arXiv preprint arXiv:2201.04232},
year = {2023}
}
Comments
We changed the title, from 'Stochastic Gradient Descent in Wasserstein Space' to 'Stochastic Gradient Descent for Barycenters in Wasserstein Space'. We expanded the literature review, included a new in-depth analysis of convergence rates, and added an appendix containing partial results for the case of possibly non-abs. continuous measures