Year: 2017
Type: preprint
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 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.
Source: arXiv (Cornell University)
Institution: Massachusetts Institute of Technology
Language: English
Subfield: Applied Mathematics
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
Awards: CAREER: Large Scale Stochastic Optimization and Statistics, Graduate Research Fellowship Program, G4504108201, Collaborative Research: Statistical Estimation with Algebraic Structure, G5137248134, G6671297155, G6858386616, Statistical and Computational Tradeoffs in High Dimensional Learning, G8876996369
OpenAlex ID: W2620318602
