# Average Individual Fairness: Algorithms, Generalization and Experiments

@inproceedings{Kearns2019AverageIF, title={Average Individual Fairness: Algorithms, Generalization and Experiments}, author={M. Kearns and A. Roth and Saeed Sharifi-Malvajerdi}, booktitle={NeurIPS}, year={2019} }

We propose a new family of fairness definitions for classification problems that combine some of the best properties of both statistical and individual notions of fairness. We posit not only a distribution over individuals, but also a distribution over (or collection of) classification tasks. We then ask that standard statistics (such as error or false positive/negative rates) be (approximately) equalized across individuals, where the rate is defined as an expectation over the classification… CONTINUE READING

#### Paper Mentions

BLOG POST

11 Citations

On the Fairness of Randomized Trials for Recommendation With Heterogeneous Demographics and Beyond

- Mathematics, Computer Science
- 2020

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 18 REFERENCES

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

- Computer Science, Mathematics
- 2018

197

An Empirical Study of Rich Subgroup Fairness for Machine Learning

- Computer Science, Mathematics
- 2019

44