AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Achieving Equalized Odds by Resampling Sensitive Attributes

Yaniv Romano, Stephen Bates, Emmanuel Candes

NeurIPS 2020 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Apply the fair-dummies equalized odds penaltyLinear regression · Synthetic regression testEqualized odds test p-value: 0.001 -> 0.452Improved
Apply the fair-dummies equalized odds penaltyLinear regression · Synthetic regression testRMSE: 2.29 -> 3.33Hurt
Apply the fair-dummies equalized odds penaltyLinear regression · Synthetic regression test, groups A=0 and A=1RMSE: A=0: 4.96 -> 3.07; A=1: 1.79 -> 3.35Mixed
Use fair-dummies models rather than fairness-unaware baselinesRegression models on MEPS and Communities and Crime · MEPS; Communities and CrimeRMSEHurt
Use fair-dummies models rather than fairness-unaware baselinesRegression models on MEPS and Communities and Crime · MEPS; Communities and CrimeEqualized odds test p-valueImproved
Use fair-dummies models rather than fairness-unaware baselinesLinear and neural-network classifiers · NurseryMisclassification errorHurt
Use the fair-dummies method instead of other procedures that appear to satisfy equalized oddsLinear and neural-network classifiers · NurseryMisclassification errorImproved
Use a neural network trained with the proposed penaltyNursery classifier with prediction sets · NurseryAverage prediction-set sizeImproved

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