2017/05/31 by Jason Altschuler, Jonathan Weed, Philippe Rigollet · 2 citations
Computer Science · Mathematics · #cs.DS #stat.ML
published as Advances in Neural Information Processing Systems 30 (NIPS 2017), 1961-1971
arxiv created 2018/02/07 · arxiv updated 2018/02/08
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 iteration, which also directly suggests a new greedy coordinate descent algorithm, Greenkhorn, with the same theoretical guarantees. Numerical simulations illustrate that Greenkhorn significantly outperforms the classical Sinkhorn algorithm in practice.