The derivatives of Sinkhorn-Knopp converge

2022/07/26 by Pauwels, Edouard, Vaiter, Samuel · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2207.12717

Abstract

We show that the derivatives of the Sinkhorn-Knopp algorithm, or iterative proportional fitting procedure, converge towards the derivatives of the entropic regularization of the optimal transport problem with a locally uniform linear convergence rate.

Cited by

• Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes

Related

• On the Convergence Rate of Sinkhorn's Algorithm
• A Sinkhorn-Newton method for entropic optimal transport
• Quantitative Stability of Regularized Optimal Transport and Convergence of Sinkhorn's Algorithm
• Quantitative Uniform Stability of the Iterative Proportional Fitting Procedure
• Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes