Obtaining Fairness Using Optimal Transport Theory

Paula Gordaliza, Eustasio Del Barrio, Gamboa Fabrice, Jean-Michel Loubes

ICML 2019 pp. 2357-2365

/icml/2019/gordaliza2019icml-obtaining/

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.

PDF ICML Semantic Scholar

Cite

Text

Gordaliza et al. "Obtaining Fairness Using Optimal Transport Theory." International Conference on Machine Learning, 2019.

Markdown

[Gordaliza et al. "Obtaining Fairness Using Optimal Transport Theory." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/gordaliza2019icml-obtaining/)

BibTeX

@inproceedings{gordaliza2019icml-obtaining,
  title     = {{Obtaining Fairness Using Optimal Transport Theory}},
  author    = {Gordaliza, Paula and Del Barrio, Eustasio and Fabrice, Gamboa and Loubes, Jean-Michel},
  booktitle = {International Conference on Machine Learning},
  year      = {2019},
  pages     = {2357-2365},
  volume    = {97},
  url       = {https://mlanthology.org/icml/2019/gordaliza2019icml-obtaining/}
}