English

A Sinkhorn-Newton method for entropic optimal transport

Optimization and Control 2018-02-12 v2 Numerical Analysis Machine Learning

Abstract

We consider the entropic regularization of discretized optimal transport and propose to solve its optimality conditions via a logarithmic Newton iteration. We show a quadratic convergence rate and validate numerically that the method compares favorably with the more commonly used Sinkhorn--Knopp algorithm for small regularization strength. We further investigate numerically the robustness of the proposed method with respect to parameters such as the mesh size of the discretization.

Keywords

Cite

@article{arxiv.1710.06635,
  title  = {A Sinkhorn-Newton method for entropic optimal transport},
  author = {Christoph Brauer and Christian Clason and Dirk Lorenz and Benedikt Wirth},
  journal= {arXiv preprint arXiv:1710.06635},
  year   = {2018}
}