On the Computational Complexity of Finding a Sparse Wasserstein Barycenter

by   Steffen Borgwardt, et al.

The discrete Wasserstein barycenter problem is a minimum-cost mass transport problem for a set of probability measures with finite support. In this paper, we show that finding a barycenter of sparse support is hard, even in dimension 2 and for only 3 measures. We prove this claim by showing that a special case of an intimately related decision problem SCMP - does there exist a measure with a non-mass-splitting transport cost and support size below prescribed bounds? - is NP-hard for all rational data. Our proof is based on a reduction from planar 3-dimensional matching and follows a strategy laid out by Spieksma and Woeginger for a reduction to planar, minimum circumference 3-dimensional matching. While we closely mirror the actual steps of their proof, the arguments themselves differ fundamentally due to the complex nature of the discrete barycenter problem. Second, we prove that given a rational measure, an optimal transport to a set of measures can be computed in polynomial time. However, the complexity of this task depends on the size of an encoding of this measure, not only on the input size to the underlying barycenter problem. We show that this distinction causes a simple proof that SCMP is in NP to fail; whether SCMP is in NP remains open.



There are no comments yet.


page 1

page 2

page 3

page 4


Wasserstein barycenters are NP-hard to compute

The problem of computing Wasserstein barycenters (a.k.a. Optimal Transpo...

Transport type metrics on the space of probability measures involving singular base measures

We develop the theory of a metric, which we call the ν-based Wasserstein...

𝒲_∞-transport with discrete target as a combinatorial matching problem

In this short note, we show that given a cost function c, any coupling π...

Optimal Art Gallery Localization is NP-hard

Art Gallery Localization (AGL) is the problem of placing a set T of broa...

On the computational complexity of blind detection of binary linear codes

In this work, we study the computational complexity of the Minimum Dista...

Interior-point Methods Strike Back: Solving the Wasserstein Barycenter Problem

Computing the Wasserstein barycenter of a set of probability measures un...

Wasserstein Coresets for Lipschitz Costs

Sparsification is becoming more and more relevant with the proliferation...
This week in AI

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