Wasserstein barycenters are NP-hard to compute
Wasserstein barycenters are NP-hard to compute
复制标题
Wasserstein 重心是 NP 难计算的
DOI:
10.1137/21m1390062
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Enric Boix
中科院分区:
文献类型:
--
作者:
Jason M. Altschuler;Enric Boix
Computing Wasserstein barycenters (a.k.a. Optimal Transport barycenters) is a fundamental problem in geometry which has recently attracted considerable attention due to many applications in data science. While there exist polynomial-time algorithms in any fixed dimension, all known running times 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.
影响因子:
2.2
作者:
Haasler, Isabel;Ringh, Axel;Chen, Yongxin;Karlsson, Johan
通讯作者:
Karlsson, Johan
影响因子:
2.5
作者:
Haasler, Isabel;Singh, Rahul;Chen, Yongxin
通讯作者:
Chen, Yongxin