Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport
Machine Learning
2021-12-07 v2 Machine Learning
Optimization and Control
Abstract
In this work we propose a batch version of the Greenkhorn algorithm for multimarginal regularized optimal transport problems. Our framework is general enough to cover, as particular cases, some existing algorithms like Sinkhorn and Greenkhorn algorithm for the bi-marginal setting, and (greedy) MultiSinkhorn for multimarginal optimal transport. We provide a complete convergence analysis, which is based on the properties of the iterative Bregman projections (IBP) method with greedy control. Global linear rate of convergence and explicit bound on the iteration complexity are obtained. When specialized to above mentioned algorithms, our results give new insights and/or improve existing ones.
Keywords
Cite
@article{arxiv.2112.00838,
title = {Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport},
author = {Vladimir Kostic and Saverio Salzo and Massimilano Pontil},
journal= {arXiv preprint arXiv:2112.00838},
year = {2021}
}
Comments
30 pages