Gadat, Sébastien, Bercu, Bernard, Bigot, Jérémie and Siviero, Emilia (2021) A Stochastic Gauss-Newton Algorithm for Regularized Semi-discrete Optimal Transport. TSE Working Paper, n. 21.1231, Toulouse, France

There is a more recent version of this item available.
[thumbnail of wp_tse_1231.pdf]
Download (2MB) | Preview


We introduce a new second order stochastic algorithm to estimate the entropically regularized optimal transport cost between two probability measures. The source measure can be arbitrary chosen, either absolutely continuous or discrete, while the target measure is assumed to be discrete. To solve the semi-dual formulation of such a regularized and semi-discrete optimal transportation problem, we propose to consider a stochastic Gauss-Newton algorithm that uses a sequence of data sampled from the source measure. This algorithm is shown to be adaptive to the geometry of the underlying convex optimization problem with no important hyperparameter to be accurately tuned. We establish the almost sure convergence and the asymptotic normality of various estimators of interest that are constructed from this stochastic Gauss-Newton algorithm. We also analyze their non-asymptotic rates of convergence for the expected quadratic risk in the absence of strong convexity of the underlying objective function. The results of numerical experiments from simulated data are also reported to illustrate the nite sample properties of this Gauss-Newton algorithm for stochastic regularized optimal transport, and to show its advantages over the use of the stochastic gradient descent, stochastic Newton and ADAM algorithms.

Item Type: Monograph (Working Paper)
Language: English
Date: 9 July 2021
Place of Publication: Toulouse, France
Uncontrolled Keywords: Stochastic optimization, Stochastic Gauss-Newton algorithm, Optimal transport, Entropic regularization, Convergence of random variables.
Divisions: TSE-R (Toulouse)
Institution: Université Toulouse 1 Capitole
Site: UT1
Date Deposited: 28 Jul 2021 12:43
Last Modified: 13 Apr 2022 07:27
OAI Identifier:

Available Versions of this Item

View Item


Downloads per month over past year