DeepAI AI Chat

The derivatives of Sinkhorn-Knopp converge

07/26/2022

∙

by Edouard Pauwels, et al.

∙

CNRS

∙

IRIT

∙

∙

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.

Edouard Pauwels
19 publications
Samuel Vaiter
20 publications

page 1

page 2

page 3

page 4

∙ 08/18/2021

Quantitative Uniform Stability of the Iterative Proportional Fitting Procedure

We establish the uniform in time stability, w.r.t. the marginals, of the...

0 George Deligiannidis, et al. ∙

∙ 10/18/2017

A Sinkhorn-Newton method for entropic optimal transport

We consider the entropic regularization of discretized optimal transport...

0 Christoph Brauer, et al. ∙

∙ 06/24/2021

Sharp Convergence Rates for Empirical Optimal Transport with Smooth Costs

We revisit the question of characterizing the convergence rate of plug-i...

0 Tudor Manole, et al. ∙

∙ 12/08/2021

Matching for causal effects via multimarginal optimal transport

Matching on covariates is a well-established framework for estimating ca...

0 Florian Gunsilius, et al. ∙

∙ 06/28/2000

Orthogonal Least Squares Algorithm for the Approximation of a Map and its Derivatives with a RBF Network

Radial Basis Function Networks (RBFNs) are used primarily to solve curve...

0 Carlo Drioli, et al. ∙

∙ 02/26/2023

Root finding via local measurement

We consider the problem of numerically identifying roots of a target fun...

0 Jonathan Landy, et al. ∙

∙ 02/02/2020

The Discrete Adjoint Method: Efficient Derivatives for Functions of Discrete Sequences

Gradient-based techniques are becoming increasingly critical in quantita...

0 Michael Betancourt, et al. ∙