License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.FORC.2023.1
URN: urn:nbn:de:0030-drops-179224
URL: https://drops.dagstuhl.de/opus/volltexte/2023/17922/
Go to the corresponding LIPIcs Volume Portal


Dwork, Cynthia ; Reingold, Omer ; Rothblum, Guy N.

From the Real Towards the Ideal: Risk Prediction in a Better World

pdf-format:
LIPIcs-FORC-2023-1.pdf (0.7 MB)


Abstract

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.

BibTeX - Entry

@InProceedings{dwork_et_al:LIPIcs.FORC.2023.1,
  author =	{Dwork, Cynthia and Reingold, Omer and Rothblum, Guy N.},
  title =	{{From the Real Towards the Ideal: Risk Prediction in a Better World}},
  booktitle =	{4th Symposium on Foundations of Responsible Computing (FORC 2023)},
  pages =	{1:1--1:17},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-272-3},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{256},
  editor =	{Talwar, Kunal},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2023/17922},
  URN =		{urn:nbn:de:0030-drops-179224},
  doi =		{10.4230/LIPIcs.FORC.2023.1},
  annote =	{Keywords: Algorithmic Fairness, Affirmative Action, Learning, Predictions, Multicalibration, Outcome Indistinguishability}
}

Keywords: Algorithmic Fairness, Affirmative Action, Learning, Predictions, Multicalibration, Outcome Indistinguishability
Collection: 4th Symposium on Foundations of Responsible Computing (FORC 2023)
Issue Date: 2023
Date of publication: 04.06.2023


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI