• Computer Science, Mathematics
  • Published in ArXiv 2017

Learning Fair Classifiers: A Regularization-Inspired Approach

@article{Bechavod2017LearningFC,
  title={Learning Fair Classifiers: A Regularization-Inspired Approach},
  author={Yahav Bechavod and Katrina Ligett},
  journal={ArXiv},
  year={2017},
  volume={abs/1707.00044}
}
We present a regularization-inspired approach for reducing bias in learned classifiers. In particular, we focus on binary classification tasks over individuals from two populations, where, as our criterion for fairness, we wish to achieve similar false positive rates in both populations, and similar false negative rates in both populations. As a proof of concept, we implement our approach and empirically evaluate its ability to achieve both fairness and accuracy, using the COMPAS scores data… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 23 CITATIONS

Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Loss-Aversively Fair Classification

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Algorithmic Fairness

VIEW 3 EXCERPTS
CITES BACKGROUND

Bias-Resilient Neural Network

VIEW 1 EXCERPT
CITES METHODS

Abstract Interpretation of Algorithmic Fairness

VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

Equality of Opportunity in Supervised Learning

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

2017. Sent to Prison by a Software Program’s

  • Adam Liptak
  • Secret Algorithms
  • 2017
VIEW 1 EXCERPT

Bias in Criminal Risk Scores Is Mathematically Inevitable, Researchers Say

  • Julia Angwin, Jeff Larson
  • 2016
VIEW 1 EXCERPT

Disciplined convex-concave programming

VIEW 1 EXCERPT

Machine Bias: There’s Software Used Across the Country to Predict Future Criminals

  • Surya Mattu Julia Angwin, Jeff Larson, Lauren Kirchner
  • And it’s Biased Against Blacks
  • 2016
VIEW 3 EXCERPTS