Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport

Abstract : This article describes a method for quickly computing the solution to the regularized optimal transport problem. It generalizes and improves upon the widely-used iterative Bregman projections algorithm (or Sinkhorn-Knopp algorithm). The idea is to overrelax the Bregman projection operators, allowing for faster convergence. In practice this corresponds to elevating the diagonal scaling factors to a given power, at each step of the algorithm. We propose a simple method for establishing global convergence by ensuring the decrease of a Lyapunov function at each step. An adaptive choice of overrelaxation parameter based on the Lyapunov function is constructed. We also suggest a heuristic to choose a suitable asymptotic overrelaxation parameter, based on a local convergence analysis. Our numerical experiments show a gain in convergence speed by an order of magnitude in certain regimes.
Liste complète des métadonnées

Contributor : Nicolas Papadakis <>
Submitted on : Tuesday, November 7, 2017 - 9:38:47 AM
Last modification on : Friday, April 12, 2019 - 4:22:51 PM

Links full text


  • HAL Id : hal-01629985, version 1
  • ARXIV : 1711.01851


Alexis Thibault, Lenaic Chizat, Charles Dossal, Nicolas Papadakis. Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport. 2017. ⟨hal-01629985⟩



Record views