Skip to Main content Skip to Navigation
Conference papers

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.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download
Contributor : Nicolas Papadakis <>
Submitted on : Monday, July 22, 2019 - 6:05:18 PM
Last modification on : Thursday, May 28, 2020 - 2:48:01 PM


Files produced by the author(s)


  • 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. NIPS'17 Workshop on Optimal Transport & Machine Learning, Dec 2017, Long Beach, United States. ⟨hal-01629985⟩



Record views


Files downloads