Wasserstein barycenters are NP-hard to compute

01/04/2021
by   Jason M. Altschuler, et al.
0

The problem of computing Wasserstein barycenters (a.k.a. Optimal Transport barycenters) has attracted considerable recent attention due to many applications in data science. While there exist polynomial-time algorithms in any fixed dimension, all known runtimes suffer exponentially in the dimension. It is an open question whether this exponential dependence is improvable to a polynomial dependence. This paper proves that unless P=NP, the answer is no. This uncovers a "curse of dimensionality" for Wasserstein barycenter computation which does not occur for Optimal Transport computation. Moreover, our hardness results for computing Wasserstein barycenters extend to approximate computation, to seemingly simple cases of the problem, and to averaging probability distributions in other Optimal Transport metrics.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/02/2022

Approximative Algorithms for Multi-Marginal Optimal Transport and Free-Support Wasserstein Barycenters

Computationally solving multi-marginal optimal transport (MOT) with squa...
03/02/2022

Discrete Optimal Transport with Independent Marginals is #P-Hard

We study the computational complexity of the optimal transport problem t...
10/16/2019

On the Computational Complexity of Finding a Sparse Wasserstein Barycenter

The discrete Wasserstein barycenter problem is a minimum-cost mass trans...
03/17/2022

Low-rank Wasserstein polynomial chaos expansions in the framework of optimal transport

A unsupervised learning approach for the computation of an explicit func...
06/14/2020

High-precision Wasserstein barycenters in polynomial time

Computing Wasserstein barycenters is a fundamental geometric problem wit...
03/10/2022

Simple Approximative Algorithms for Free-Support Wasserstein Barycenters

Computing Wasserstein barycenters of discrete measures has recently attr...
08/07/2020

Polynomial-time algorithms for Multimarginal Optimal Transport problems with structure

Multimarginal Optimal Transport (MOT) has recently attracted significant...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.