On preserving non-discrimination when combining expert advice
By Avrim Blum, Suriya Gunasekar, Thodoris Lykouris, Nati Srebro. 2018
31 citations recorded by the source corpus.
We study the interplay between sequential decision making and avoiding discrimination against protected groups, when examples arrive online and do not follow distributional assumptions. We consider the most basic extension of classical online learning: "Given a class of predictors that are individually non-discriminatory with respect to a particular metric, how can we combine them to perform as well as the best predictor, while preserving non-discrimination?" Surprisingly we show that this task is unachievable for the prevalent notion of "equalized odds" that requires equal false negative rates and equal false positive rates across groups. On the positive side, for another notion of non-discrimination, "equalized error rates", we show that running separate instances of the classical multiplicative weights algorithm for each group achieves this guarantee. Interestingly, even for this notion, we show that algorithms with stronger performance guarantees than multiplicative weights cannot preserve non-discrimination.
Subfields: Safety Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Safety Research
- Aaron Roth
- Zhiwei Steven Wu
- Vijay Kamble
- Katrina Ligett
- Swati Gupta
- Yahav Bechavod
- Dana Pessach
- Erez Shmueli
Citations in the corpus
- Equal Opportunity in Online Classification with Partial Feedback (2019, background): “Recently, [7] considered the problem of enforcing statistical fairness in a full information online learning setting, but from a very different perspective.”
- Individual Fairness in Hindsight (2018, background): “Relevant paper in this regard is Blum et al. (2018), which shows the incompatibility of ensuring certain notions of group fairness and achieving good classifications in the online learning problem of combining fair expert classifiers when the arrivals are adversarial.”