Obtaining Fairness using Optimal Transport Theory

Paula Gordaliza, Eustasio Del Barrio, Gamboa Fabrice, Jean-Michel Loubes
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:2357-2365, 2019.

Abstract

In the fair classification setup, we recast the links between fairness and predictability in terms of probability metrics. We analyze repair methods based on mapping conditional distributions to the Wasserstein barycenter. We propose a Random Repair which yields a tradeoff between minimal information loss and a certain amount of fairness.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-gordaliza19a, title = {Obtaining Fairness using Optimal Transport Theory}, author = {Gordaliza, Paula and Barrio, Eustasio Del and Fabrice, Gamboa and Loubes, Jean-Michel}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {2357--2365}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/gordaliza19a/gordaliza19a.pdf}, url = {https://proceedings.mlr.press/v97/gordaliza19a.html}, abstract = {In the fair classification setup, we recast the links between fairness and predictability in terms of probability metrics. We analyze repair methods based on mapping conditional distributions to the Wasserstein barycenter. We propose a Random Repair which yields a tradeoff between minimal information loss and a certain amount of fairness.} }
Endnote
%0 Conference Paper %T Obtaining Fairness using Optimal Transport Theory %A Paula Gordaliza %A Eustasio Del Barrio %A Gamboa Fabrice %A Jean-Michel Loubes %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-gordaliza19a %I PMLR %P 2357--2365 %U https://proceedings.mlr.press/v97/gordaliza19a.html %V 97 %X In the fair classification setup, we recast the links between fairness and predictability in terms of probability metrics. We analyze repair methods based on mapping conditional distributions to the Wasserstein barycenter. We propose a Random Repair which yields a tradeoff between minimal information loss and a certain amount of fairness.
APA
Gordaliza, P., Barrio, E.D., Fabrice, G. & Loubes, J.. (2019). Obtaining Fairness using Optimal Transport Theory. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:2357-2365 Available from https://proceedings.mlr.press/v97/gordaliza19a.html.

Related Material