Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization
Not on the map. Why?
Abstract (arXiv)
Fairness researchers in machine learning (ML) have coalesced around several fairness criteria which provide formal definitions of what it means for an ML model to be fair. However, these criteria have some serious limitations. We identify four key shortcomings of these formal fairness criteria, and aim to help to address them by extending performative prediction to include a distributionally robust objective.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 36 references that are in the map. First posted on arXiv 12 Jul 2022.
Builds on
16 of 36 references.
References · 16
- 2021Convex optimizationcited by 2,515
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
- 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
- 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
- 2017Algorithmic decision making and the cost of fairnesscited by 403
- 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
- 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
- 2020Performative Predictioncited by 327
- 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
- 2015Strategic Classificationcited by 257
- 2018The Social Cost of Strategic Classificationcited by 105
- 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 96
4 more
- 2020Performative Prediction in a Stateful Worldcited by 90
- 2018The Disparate Effects of Strategic Manipulationcited by 75
- 2020Distributionally Robust Losses for Latent Covariate Mixturescited by 58
- 2021Approximate Regions of Attraction in Learning with Decision-Dependent Distributionscited by 11
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.