Approximating the Quadratic Transportation Metric in Near-Linear Time

10/23/2018
by   Jason Altschuler, et al.
0

Computing the quadratic transportation metric (also called the 2-Wasserstein distance or root mean square distance) between two point clouds, or, more generally, two discrete distributions, is a fundamental problem in machine learning, statistics, computer graphics, and theoretical computer science. A long line of work has culminated in a sophisticated geometric algorithm due to AgaSha14, which runs in time Õ(n^3/2), where n is the number of points. However, obtaining faster algorithms has proven difficult since the 2-Wasserstein distance is known to have poor sketching and embedding properties, which limits the effectiveness of geometric approaches. In this paper, we give an extremely simple deterministic algorithm with Õ(n) runtime by using a completely different approach based on entropic regularization, approximate Sinkhorn scaling, and low-rank approximations of Gaussian kernel matrices. We give explicit dependence of our algorithm on the dimension and precision of the approximation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/14/2020

High-precision Wasserstein barycenters in polynomial time

Computing Wasserstein barycenters is a fundamental geometric problem wit...
research
02/22/2019

Preconditioning for the Geometric Transportation Problem

In the geometric transportation problem, we are given a collection of po...
research
07/06/2023

A Near-Linear Time Algorithm for the Chamfer Distance

For any two point sets A,B ⊂ℝ^d of size up to n, the Chamfer distance fr...
research
04/27/2020

Hierarchical Low-Rank Approximation of Regularized Wasserstein distance

Sinkhorn divergence is a measure of dissimilarity between two probabilit...
research
01/04/2010

Comparing Distributions and Shapes using the Kernel Distance

Starting with a similarity function between objects, it is possible to d...
research
07/18/2023

Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces

This paper presents a framework for computing the Gromov-Wasserstein pro...
research
10/20/2020

Wasserstein K-Means for Clustering Tomographic Projections

Motivated by the 2D class averaging problem in single-particle cryo-elec...

Please sign up or login with your details

Forgot password? Click here to reset