Algorithms for euclidean regularised Optimal Transport

This paper considers Optimal Transport problem regularised by square of euclidean $\ell_2$-norm, provides theoretical guarantees on Sinkhorn-Knopp algorithm, Accelerated Gradient Descent, Accelerated Alternating Minimisation, and Coordinate Linear Variance Reduction algorithms' iteration complexities, and compares practical efficiency of these methods and their analogues applied to entropy regularised Optimal Transport problem by numerical experiments on MNIST dataset.

[1]  Zesen Wang,et al.  Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs , 2023, ArXiv.

[2]  Stephen J. Wright,et al.  Coordinate Linear Variance Reduction for Generalized Linear Programming , 2021, NeurIPS.

[3]  Justin Solomon,et al.  Continuous Regularized Wasserstein Barycenters , 2020, NeurIPS.

[4]  Alexander V. Gasnikov,et al.  On a Combination of Alternating Minimization and Nesterov's Momentum , 2019, ICML.

[5]  D. Lorenz,et al.  Quadratically Regularized Optimal Transport , 2019, Applied Mathematics & Optimization.

[6]  Michael I. Jordan,et al.  On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms , 2019, ICML.

[7]  Gabriel Peyré,et al.  Computational Optimal Transport , 2018, Found. Trends Mach. Learn..

[8]  Alexander Gasnikov,et al.  Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm , 2018, ICML.

[9]  Vivien Seguy,et al.  Smooth and Sparse Optimal Transport , 2017, AISTATS.

[10]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[11]  Gustavo K. Rohde,et al.  Optimal Mass Transport: Signal processing and machine-learning applications , 2017, IEEE Signal Processing Magazine.

[12]  Jason Altschuler,et al.  Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration , 2017, NIPS.

[13]  Montacer Essid,et al.  Quadratically-Regularized Optimal Transport on Graphs , 2017, SIAM J. Sci. Comput..

[14]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[15]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[16]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

[17]  C. Villani.  Optimal Transport: Old and New , 2008 .

[18]  L. Kantorovich.  On the Translocation of Masses , 2006 .

[19]  Richard Sinkhorn.  Diagonal equivalence to matrices with prescribed row and column sums. II , 1974 .

[20]  Arthur Cayley,et al.  The Collected Mathematical Papers: On Monge's “Mémoire sur la théorie des déblais et des remblais” , 2009 .