Abstract
This paper addresses the Optimal Transport problem, which is regularized by the square of Euclidean \(\ell _2\)-norm. It offers theoretical guarantees regarding the iteration complexities of the Sinkhorn–Knopp algorithm, Accelerated Gradient Descent, Accelerated Alternating Minimisation, and Coordinate Linear Variance Reduction algorithms. Furthermore, the paper compares the practical efficiency of these methods and their counterparts when applied to the entropy-regularized Optimal Transport problem. This comparison is conducted through numerical experiments carried out on the MNIST dataset.
The research was supported by Russian Science Foundation (project No. 23-11-00229), https://rscf.ru/en/project/23-11-00229/, and by the grant of support for leading scientific schools NSh775.2022.1.1.
D. A. Pasechnyuk and M. Persiianov—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Repository is available at https://github.com/MuXauJl11110/Euclidean-Regularised-Optimal-Transport.
References
Altschuler, J., Niles-Weed, J., Rigollet, P.: Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration. Adv. Neural Inf. Process. 30 (2017)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223. PMLR (2017)
Blondel, M., Seguy, V., Rolet, A.: Smooth and sparse optimal transport. In: International Conference on Artificial Intelligence and Statistics, pp. 880–889. PMLR (2018)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. Adv. Neural Inf. Process. Syst. 26 (2013)
Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141–142 (2012)
Dvurechensky, P., Gasnikov, A., Kroshnin, A.: Computational optimal transport: complexity by accelerated gradient descent is better than by Sinkhorn’s algorithm. In: International Conference on Machine Learning, pp. 1367–1376. PMLR (2018)
Essid, M., Solomon, J.: Quadratically regularized optimal transport on graphs. SIAM J. Sci. Comput. 40(4), A1961–A1986 (2018)
Guminov, S., Dvurechensky, P., Tupitsa, N., Gasnikov, A.: On a combination of alternating minimization and Nesterov’s momentum. In: International Conference on Machine Learning, pp. 3886–3898. PMLR (2021)
Kantorovich, L.V.: On the translocation of masses. Dokl. Akad. Nauk. USSR (NS) 37, 199–201 (1942)
Kolouri, S., Park, S.R., Thorpe, M., Slepcev, D., Rohde, G.K.: Optimal mass transport: signal processing and machine-learning applications. IEEE Signal Process. Mag. 34(4), 43–59 (2017)
Li, L., Genevay, A., Yurochkin, M., Solomon, J.M.: Continuous regularized wasserstein barycenters. Adv. Neural. Inf. Process. Syst. 33, 17755–17765 (2020)
Lin, T., Ho, N., Jordan, M.: On efficient optimal transport: an analysis of greedy and accelerated mirror descent algorithms. In: International Conference on Machine Learning, pp. 3982–3991. PMLR (2019)
Lindbäck, J., Wang, Z., Johansson, M.: Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs. arXiv preprint arXiv:2305.18483 (2023)
Lorenz, D.A., Manns, P., Meyer, C.: Quadratically regularized optimal transport. Appl. Math. Optim. 83(3), 1919–1949 (2019). https://doi.org/10.1007/s00245-019-09614-w
Monge, G.: Mémoire sur la théorie des déblais et des remblais. Mem. Math. Phys. Acad. Royale Sci., pp. 666–704 (1781)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, New York (2003). https://doi.org/10.1007/978-1-4419-8853-9
Peyré, G., Cuturi, M., et al.: Computational optimal transport. In: Foundations and Trends® in Machine Learning (2019)
Sinkhorn, R.: Diagonal equivalence to matrices with prescribed row and column sums. Am. Math. Mon. 74(4), 402–405 (1967)
Song, C., Lin, C.Y., Wright, S., Diakonikolas, J.: Coordinate linear variance reduction for generalized linear programming. Adv. Neural. Inf. Process. Syst. 35, 22049–22063 (2022)
Villani, C., et al.: Optimal Transport: Old and New, vol. 338. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-540-71050-9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pasechnyuk, D.A., Persiianov, M., Dvurechensky, P., Gasnikov, A. (2023). Algorithms for Euclidean-Regularised Optimal Transport. In: Olenev, N., Evtushenko, Y., Jaćimović, M., Khachay, M., Malkova, V. (eds) Optimization and Applications. OPTIMA 2023. Lecture Notes in Computer Science, vol 14395. Springer, Cham. https://doi.org/10.1007/978-3-031-47859-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-47859-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47858-1
Online ISBN: 978-3-031-47859-8
eBook Packages: Computer ScienceComputer Science (R0)