Algorithms for Euclidean-regularised Optimal Transport

MaRDI QIDQ6442229zbMATH OpenFDO

Authors D. A. Pasechnyuk, Michael Persiianov, Pavel Dvurechensky, A. V. Gasnikov

Publication date 1 July 2023

Has companion code repository https://github.com/muxaujl11110/euclidean-regularised-optimal-transport

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10)

Abstract: This paper considers Optimal Transport problem regularised by square of euclidean $el{l}_2$-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.

This page was built for publication: Algorithms for Euclidean-regularised Optimal Transport

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6442229)