Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Reweighting samples under covariate shift using a Wasserstein distance criterion

Abstract : Considering two random variables with different laws to which we only have access through finite size iid samples, we address how to reweight the first sample so that its empirical distribution converges towards the true law of the second sample as the size of both samples goes to infinity. We study an optimal reweighting that minimizes the Wasserstein distance between the empirical measures of the two samples, and leads to an expression of the weights in terms of Nearest Neighbors. The consistency and some asymptotic convergence rates in terms of expected Wasserstein distance are derived, and do not need the assumption of absolute continuity of one random variable with respect to the other. These results have some application in Uncertainty Quantification for decoupled estimation and in the bound of the generalization error for the Nearest Neighbor Regression under covariate shift.
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Touboul Adrien Connect in order to contact the contributor
Submitted on : Friday, October 16, 2020 - 12:44:41 PM
Last modification on : Friday, January 15, 2021 - 5:37:41 PM


Files produced by the author(s)


  • HAL Id : hal-02968059, version 1
  • ARXIV : 2010.09267



Julien Reygner, Adrien Touboul. Reweighting samples under covariate shift using a Wasserstein distance criterion. 2020. ⟨hal-02968059⟩



Record views


Files downloads