Corpus ID: 219636391

Fair Regression with Wasserstein Barycenters

@article{Chzhen2020FairRW,
  title={Fair Regression with Wasserstein Barycenters},
  author={Evgenii Chzhen and C. Denis and Mohamed Hebiri and L. Oneto and M. Pontil},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.07286}
}
  • Evgenii Chzhen, C. Denis, +2 authors M. Pontil
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • We study the problem of learning a real-valued function that satisfies the Demographic Parity constraint. It demands the distribution of the predicted output to be independent of the sensitive attribute. We consider the case that the sensitive attribute is available for prediction. We establish a connection between fair regression and optimal transport theory, based on which we derive a close form expression for the optimal fair predictor. Specifically, we show that the distribution of this… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    A minimax framework for quantifying risk-fairness trade-off in regression

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES
    Learning Fair Representations
    • 645
    • PDF
    Equality of Opportunity in Supervised Learning
    • 1,043
    • PDF
    Topics in Optimal Transportation
    • 3,338
    The Design of Experiments
    • 3,586
    HIGH-DIMENSIONAL GENERALIZED LINEAR MODELS AND THE LASSO
    • 588
    • PDF
    Barycenters in the Wasserstein Space
    • 366
    • PDF