Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration

05/26/2017
by   Jason Altschuler, et al.
0

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, and provides guidance towards parameter tuning for this algorithm. This result relies on a new analysis of Sinkhorn iterations that also directly suggests a new algorithm Greenkhorn with the same theoretical guarantees. Numerical simulations illustrate that Greenkhorn significantly outperforms the classical Sinkhorn algorithm in practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/08/2021

Optimal Transport in the Face of Noisy Data

Optimal transport distances are popular and theoretically well understoo...
research
02/25/2021

Improving Approximate Optimal Transport Distances using Quantization

Optimal transport (OT) is a popular tool in machine learning to compare ...
research
07/14/2021

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

The current best practice for computing optimal transport (OT) is via en...
research
01/17/2023

Faster Sinkhorn's Algorithm with Small Treewidth

Computing optimal transport (OT) distances such as the earth mover's dis...
research
05/03/2020

A Study of Performance of Optimal Transport

We investigate the problem of efficiently computing optimal transport (O...
research
06/17/2022

Distances for Comparing Multisets and Sequences

Measuring the distance between data points is fundamental to many statis...
research
05/19/2020

An optimal transport approach to data compression in distributionally robust control

We consider the problem of controlling a stochastic linear time-invarian...

Please sign up or login with your details

Forgot password? Click here to reset