DeepAI AI Chat
Log In Sign Up

The derivatives of Sinkhorn-Knopp converge

07/26/2022
by   Edouard Pauwels, et al.
CNRS
IRIT
0

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.

READ FULL TEXT

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...
10/18/2017

A Sinkhorn-Newton method for entropic optimal transport

We consider the entropic regularization of discretized optimal transport...
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...
12/08/2021

Matching for causal effects via multimarginal optimal transport

Matching on covariates is a well-established framework for estimating ca...
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...
02/26/2023

Root finding via local measurement

We consider the problem of numerically identifying roots of a target fun...
02/02/2020

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

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