AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

On the Impossibility of Non-trivial Accuracy in Presence of Fairness Constraints

AAAI 2022 · Learning theory and algorithms › Fairness · approach: Post-processing and transport for fairness · 6 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
impose exact equal-opportunity without differential privacyPredictors on certain probabilistic data sources · Certain probabilistic data sourcesaccuracy relative to the best constant predictorHurt
allow probabilistic labels and use the Bayes classifierBayes classifier · Probabilistic data sources constructed in Proposition 7opportunity differenceMixed
allow probabilistic labels and use the soft target predictor QSoft target predictor · Probabilistic data sources constructed in Proposition 7opportunity differenceHurt
require positive probability of Q>1/2 and Q<1/2 in each protected groupPredictors on probabilistic data sources · Sources satisfying Theorem 9non-trivial accuracy and equal-opportunity compatibilityHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy