Abstract
Considering two random variables with different laws to which we only have access through finite size i.i.d 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.
Funding Statement
The research work of AT has been carried out under the leadership of the Technological Research Institute SystemX, and therefore granted with public funds within the scope of the French Program ‘Investissements d’Avenir’.
Acknowledgments
This work was motivated by a collaboration with P. Benjamin, F. Mangeant and M. Yagoubi. We also benefited from fruitful discussions with G. Biau and A. Guyader. Last, we thank two anonymous referees for their careful reading of the article, and their numerous suggestions which allowed to greatly improve the presentation of this work.
Citation
Julien Reygner. Adrien Touboul. "Reweighting samples under covariate shift using a Wasserstein distance criterion." Electron. J. Statist. 16 (1) 3278 - 3314, 2022. https://doi.org/10.1214/21-EJS1974
Information
