Abstract
AbstractMultimarginal Optimal Transport (MOT) has attracted significant interest due to applications in machine learning, statistics, and the sciences. However, in most applications, the success of MOT is severely limited by a lack of efficient algorithms. Indeed, MOT in general requires exponential time in the number of marginals k and their support sizes n. This paper develops a general theory about what “structure” makes MOT solvable in $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
time. We develop a unified algorithmic framework for solving MOT in $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
time by characterizing the structure that different algorithms require in terms of simple variants of the dual feasibility oracle. This framework has several benefits. First, it enables us to show that the Sinkhorn algorithm, which is currently the most popular MOT algorithm, requires strictly more structure than other algorithms do to solve MOT in $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
time. Second, our framework makes it much simpler to develop $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
time algorithms for a given MOT problem. In particular, it is necessary and sufficient to (approximately) solve the dual feasibility oracle—which is much more amenable to standard algorithmic techniques. We illustrate this ease-of-use by developing $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
-time algorithms for three general classes of MOT cost structures: (1) graphical structure; (2) set-optimization structure; and (3) low-rank plus sparse structure. For structure (1), we recover the known result that Sinkhorn has $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
runtime; moreover, we provide the first $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
time algorithms for computing solutions that are exact and sparse. For structures (2)-(3), we give the first $$\mathrm {poly}(n,k)$$
poly
(
n
,
k
)
time algorithms, even for approximate computation. Together, these three structures encompass many—if not most—current applications of MOT.
Funder
National Science Foundation
TwoSigma PhD fellowship
Siebel PhD Fellowship
Publisher
Springer Science and Business Media LLC
Subject
General Mathematics,Software
Reference93 articles.
1. Agrawal, S., Ding, Y., Saberi, A., Ye, Y.: Price of correlations in stochastic optimization. Oper. Res. 60(1), 150–162 (2012)
2. Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. SIAM J. on Math. Anal. 43(2), 904–924 (2011)
3. Akagi, Y., Tanaka, Y., Iwata, T., Kurashima, T., Toda, H.: Probabilistic optimal transport based on collective graphical models. (2020). Preprint at arXiv:2006.08866
4. Altschuler, J., Bach, F., Rudi, A., Niles-Weed, J.: Massively scalable Sinkhorn distances via the Nyström method. Adv. in Neural Inf. Process. Syst. 32, 4429–4439 (2019)
5. Altschuler, J., Weed, J., Rigollet, P.: Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration. Advances in Neural Information Processing Systems (2017)
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献