On the Convergence Rate of Sinkhorn's Algorithm
Abstract
We study Sinkhorn's algorithm for solving the entropically regularized optimal transport problem. Its iterate is shown to satisfy where denotes relative entropy and the optimal coupling. This holds for a large class of cost functions and marginals, including quadratic cost with subgaussian marginals. We also obtain the rate for the dual suboptimality and for the marginal entropies. More precisely, we derive non-asymptotic bounds, and in contrast to previous results on linear convergence that are limited to bounded costs, our estimates do not deteriorate exponentially with the regularization parameter. We also obtain a stability result for as a function of the marginals, quantified in relative entropy.
Cite
@article{arxiv.2212.06000,
title = {On the Convergence Rate of Sinkhorn's Algorithm},
author = {Promit Ghosal and Marcel Nutz},
journal= {arXiv preprint arXiv:2212.06000},
year = {2025}
}
Comments
Forthcoming in 'Mathematics of Operations Research'