Abstract
This paper presents primal heuristics for the computation of Wasserstein Barycenters of a given set of discrete probability measures. The computation of a Wasserstein Barycenter is formulated as an optimization problem over the space of discrete probability measures. In practice, the barycenter is a discrete probability measure which minimizes the sum of the pairwise Wasserstein distances between the barycenter itself and each input measure. While this problem can be formulated using Linear Programming techniques, it remains a challenging problem due to the size of real-life instances. In this paper, we propose simple but efficient primal heuristics, which exploit the properties of the optimal plan obtained while computing the Wasserstein Distance between a pair of probability measures. In order to evaluate the proposed primal heuristics, we have performed extensive computational tests using random Gaussian distributions, the MNIST handwritten digit dataset, and the Fashion MNIST dataset introduced by Zalando. We also used Translated MNIST, a modification of MNIST which contains original images, rescaled randomly and translated into a larger image. We compare the barycenters computed by our heuristics with the exact solutions obtained with a commercial Linear Programming solver, and with a state-of-the-art algorithm based on Gaussian convolutions. Our results show that the proposed heuristics yield in very short run time and an average optimality gap significantly smaller than 1%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. SIAM J. Math. Anal. 43(2), 904–924 (2011)
Ahuja, R.K., Magnanti, T.L., Orlin, J.B.: Network flows: Theory, Algorithms, and Applications. Cambridge, Mass.: Alfred P. Sloan School of Management, Massachusetts Institute of Technology (1988)
Anderes, E., Borgwardt, S., Miller, J.: Discrete Wasserstein Barycenters: optimal transport for discrete data. Math. Methods Oper. Res. 84(2), 389–409 (2016)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv preprint arXiv:1701.07875 (2017)
Auricchio, G., Bassetti, F., Gualandi, S., Veneroni, M.: Computing kantorovich-wasserstein distances on \( d \)-dimensional histograms using \((d+ 1) \)-partite graphs. In: Advances in Neural Information Processing Systems, pp. 5793–5803 (2018)
Auricchio, G., Bassetti, F., Gualandi, S., Veneroni, M.: Computing Wasserstein Barycenters via linear programming. In: Rousseau, L.-M., Stergiou, K. (eds.) CPAIOR 2019. LNCS, vol. 11494, pp. 355–363. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-19212-9_23
Bassetti, F., Gualandi, S., Veneroni, M.: On the computation of Kantorovich-Wasserstein distances between 2D-histograms by uncapacitated minimum cost flows. arXiv preprint arXiv:1804.00445 (2018)
Bonneel, N., Coeurjolly, D.: Spot: sliced partial optimal transport. ACM Trans. Graph. 38(4), 1–13 (2019)
Bonneel, N., Van De Panne, M., Paris, S., Heidrich, W.: Displacement interpolation using Lagrangian mass transport. ACM Trans. Graph. 30, 158–160 (2011)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, pp. 2292–2300 (2013)
Cuturi, M., Doucet, A.: Fast computation of Wasserstein Barycenters. In: International Conference on Machine Learning, pp. 685–693 (2014)
Dvurechenskii, P., Dvinskikh, D., Gasnikov, A., Uribe, C., Nedich, A.: Decentralize and randomize: faster algorithm for Wasserstein Barycenters. In: Advances in Neural Information Processing Systems, pp. 10760–10770 (2018)
Flamary, R., Courty, N.: POT: Python Optimal Transport library (2017). https://github.com/rflamary/POT
Goldberg, A.V., Tardos, É., Tarjan, R.: Network flow algorithms. Cornell University Operations Research and Industrial Engineering, Technical report (1989)
Koopmans, T.C.: Optimum utilization of the transportation system. Econom. J. Econom. Soc. 17, 136–146 (1949)
Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: International Conference on Machine Learning, pp. 957–966 (2015)
LeCun, Y., Cortes, C., Burges, C.J.: MNIST dataset. http://yann.lecun.com/exdb/mnist/. Accessed 12 Mar 2019
Levina, E., Bickel, P.: The Earth mover’s distance is the mallows distance: some insights from statistics. In: IEEE International Conference on Computer Vision, vol. 2, pp. 251–256 (2001)
Ling, H., Okada, K.: An efficient earth mover’s distance algorithm for robust histogram comparison. IEEE Trans. Pattern Anal. Mach. Intell. 29(5), 840–853 (2007)
Luise, G., Salzo, S., Pontil, M., Ciliberto, C.: Sinkhorn Barycenters with free support via Frank-Wolfe algorithm. arXiv preprint arXiv:1905.13194 (2019)
Monge, G.: Mémoire sur la théorie des déblais et des remblais. Histoire de l’Académie Royale des Sciences de Paris (1781)
Panaretos, V.M., Zemel, Y.: Statistical aspects of Wasserstein distances. Ann. Rev. Stat. Appl. 6, 405–431 (2019)
Pele, O., Werman, M.: Fast and robust earth mover’s distances. In: IEEE International Conference on Computer vision, pp. 460–467 (2009)
Peyré, G., Cuturi, M., et al.: Computational optimal transport. Found. Trends Mach. Learn. 11(5–6), 355–607 (2019)
Qian, Y., Pan, S.: A proximal ALM method for computing Wasserstein Barycenter in d2-clustering of discrete distributions. arXiv preprint arXiv:1809.05990 (2018)
Rabin, J., Ferradans, S., Papadakis, N.: Adaptive color transfer with relaxed optimal transport. In: 2014 IEEE International Conference on Image Processing, pp. 4852–4856 (2014)
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vision 40(2), 99–121 (2000)
Santambrogio, F.: Optimal Transport for Applied Mathematicians, pp. 99–102. Birkäuser (2015)
Solomon, J., et al.: Convolutional Wasserstein distances: efficient optimal transportation on geometric domains. ACM Trans. Graph. 34(4), 66 (2015)
Staib, M., Claici, S., Solomon, J.M., Jegelka, S.: Parallel streaming Wasserstein Barycenters. In: Advances in Neural Information Processing Systems, pp. 2647–2658 (2017)
Vershik, A.M.: Long history of the Monge-Kantorovich transportation problem. Math. Intell. 35(4), 1–9 (2013)
Villani, C.: Optimal Transport: Old and New, vol. 338. Springer, Heidelberg (2008)
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Bouchet, PY., Gualandi, S., Rousseau, LM. (2020). Primal Heuristics for Wasserstein Barycenters. In: Hebrard, E., Musliu, N. (eds) Integration of Constraint Programming, Artificial Intelligence, and Operations Research. CPAIOR 2020. Lecture Notes in Computer Science(), vol 12296. Springer, Cham. https://doi.org/10.1007/978-3-030-58942-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-58942-4_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58941-7
Online ISBN: 978-3-030-58942-4
eBook Packages: Computer ScienceComputer Science (R0)