Abstract
We consider the numerical solution of the discrete multi-marginal optimal transport (MOT) by means of the Sinkhorn algorithm. In general, the Sinkhorn algorithm suffers from the curse of dimensionality with respect to the number of marginals. If the MOT cost function decouples according to a tree or circle, its complexity is linear in the number of marginal measures. In this case, we speed up the convolution with the radial kernel required in the Sinkhorn algorithm via non-uniform fast Fourier methods. Each step of the proposed accelerated Sinkhorn algorithm with a tree-structured cost function has a complexity of O(KN) instead of the classical O(KN2) for straightforward matrix–vector operations, where K is the number of marginals and each marginal measure is supported on, at most, N points. In the case of a circle-structured cost function, the complexity improves from O(KN3) to O(KN2). This is confirmed through numerical experiments.
Funder
Federal Ministry of Education and Research
Deutsche Forschungsgemeinschaft
Subject
Computational Mathematics,Computational Theory and Mathematics,Numerical Analysis,Theoretical Computer Science
Reference57 articles.
1. Computational Optimal Transport: With Applications to Data Science;Cuturi;Found. Trends Mach. Learn.,2019
2. Villani, C. (2009). Optimal Transport: Old and New, Springer.
3. Beier, F., von Lindheim, J., Neumayer, S., and Steidl, G. (2021). Unbalanced multi-marginal optimal transport. arXiv.
4. Wasserstein barycentric coordinates: Histogram regression using optimal transport;Bonneel;ACM Trans. Graph.,2016
5. Wasserstein loss for image synthesis and restoration;Tartavel;SIAM J. Imaging Sci.,2016
Cited by
2 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