2026-07-23T17:33:55Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:17922 2024-03-06T11:00:26Z ddc:004 open_access

From the Real Towards the Ideal: Risk Prediction in a Better World Dwork, Cynthia Reingold, Omer Rothblum, Guy N. Algorithmic Fairness Affirmative Action Learning Predictions Multicalibration Outcome Indistinguishability Prediction algorithms assign scores in [0,1] to individuals, often interpreted as "probabilities" of a positive outcome, for example, of repaying a loan or succeeding in a job. Success, however, rarely depends only on the individual: it is a function of the individual’s interaction with the environment, past and present. Environments do not treat all demographic groups equally. We initiate the study of corrective transformations τ that map predictors of success in the real world to predictors in a better world. In the language of algorithmic fairness, letting p^* denote the true probabilities of success in the real, unfair, world, we characterize the transformations τ for which it is feasible to find a predictor q̃ that is indistinguishable from τ(p^*). The problem is challenging because we do not have access to probabilities or even outcomes in a better world. Nor do we have access to probabilities p^* in the real world. The only data available for training are outcomes from the real world. We obtain a complete characterization of when it is possible to learn predictors that are indistinguishable from τ(p^*), in the form of a simple-to-state criterion describing necessary and sufficient conditions for doing so. This criterion is inextricably bound with the very existence of uncertainty. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Cynthia Dwork and Omer Reingold and Guy N. Rothblum 2023 Is Part Of LIPIcs, Volume 256, 4th Symposium on Foundations of Responsible Computing (FORC 2023) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.FORC.2023.1 urn:nbn:de:0030-drops-179224 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2023.1 eng https://creativecommons.org/licenses/by/4.0/legalcode