Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settings

10 February 2022

Papers citing "Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settings"

9 / 9 papers shown

Title
The Flaws of Policies Requiring Human Oversight of Government Algorithms Ben Green 75 117 0 10 Sep 2021
Testing for concept shift online V. Vovk 48 22 0 28 Dec 2020
How Do Fair Decisions Fare in Long-term Qualification? Xueru Zhang Ruibo Tu Yang Liu M. Liu Hedvig Kjellström Kun Zhang Cheng Zhang 85 75 0 21 Oct 2020
Robust Fairness under Covariate Shift Ashkan Rezaei Anqi Liu Omid Memarrast Brian Ziebart TTA OOD 126 86 0 11 Oct 2020
Performative Prediction Juan C. Perdomo Tijana Zrnic Celestine Mendler-Dünner Moritz Hardt 158 322 0 16 Feb 2020
Fairness Without Demographics in Repeated Loss Minimization Tatsunori B. Hashimoto Megha Srivastava Hongseok Namkoong Percy Liang FaML 117 585 0 20 Jun 2018
Delayed Impact of Fair Machine Learning Lydia T. Liu Sarah Dean Esther Rolf Max Simchowitz Moritz Hardt FaML 85 478 0 12 Mar 2018
Runaway Feedback Loops in Predictive Policing D. Ensign Sorelle A. Friedler Scott Neville C. Scheidegger Suresh Venkatasubramanian 63 347 0 29 Jun 2017
Equality of Opportunity in Supervised Learning Moritz Hardt Eric Price Nathan Srebro FaML 236 4,341 0 07 Oct 2016