Wasserstein barycenters are NP-hard to compute

by   Jason M. Altschuler, et al.

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.


page 1

page 2

page 3

page 4


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

Computationally solving multi-marginal optimal transport (MOT) with squa...

On the Computational Complexity of Finding a Sparse Wasserstein Barycenter

The discrete Wasserstein barycenter problem is a minimum-cost mass trans...

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

A unsupervised learning approach for the computation of an explicit func...

High-precision Wasserstein barycenters in polynomial time

Computing Wasserstein barycenters is a fundamental geometric problem wit...

Simple Approximative Algorithms for Free-Support Wasserstein Barycenters

Computing Wasserstein barycenters of discrete measures has recently attr...

Hardness results for Multimarginal Optimal Transport problems

Multimarginal Optimal Transport (MOT) is the problem of linear programmi...

Streaming computation of optimal weak transport barycenters

We introduce the weak barycenter of a family of probability distribution...

Please sign up or login with your details

Forgot password? Click here to reset