Abstract 

Computing optimal transport distances such as the earth mover’s distance is a fundamental problem in machine learning, statistics, and computer vision. Despite the recent introduction of several algorithms with good empirical performance, it is unknown whether general optimal transport distances can be approximated in near-linear time. This paper demonstrates that this ambitious goal is in fact achieved by Cuturi’s Sinkhorn Distances. This result relies on a new analysis of Sinkhorn iterations, which also directly suggests a new greedy coordinate descent algorithm G REENKHORN with the same theoretical guarantees. Numerical simulations illustrate that G REENKHORN significantly outperforms the classical S INKHORN algorithm in practice. Dedicated to the memory of Michael B. Cohen