AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Long-Term Fairness with Unknown Dynamics

Tongxin Yin, Reilly Raab, Mingyan Liu, Yang Liu

NeurIPS 2023 · Learning theory and algorithms › Fairness · approach: Causal and policy fairness in decisions

Read the paper

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
Optimize cumulative true-positive rate with UCBFair instead of greedy myopic classificationClassifier-population system · Synthetic population, demographic parityqualification rateImproved
Optimize immediate utility with the Greedy Baseline rather than long-term RLClassifier-population system · Synthetic population, demographic parityqualification rateHurt
Use DRL with scheduled disparity regularization instead of UCBFairClassifier-population system · Adult dataset, demographic paritydemographic parity violationMixed
Use UCBFair to optimize long-term fairness rather than myopic classificationClassifier-population system · Adult dataset, demographic paritytrue-positive classificationsImproved
Optimize qualification rate parity with reinforcement learningUCBFair and DRL · Synthetic population, qualification rate parityqualification rate parityImproved
Use UCBFair instead of DRL for qualification rate parityUCBFair · Synthetic population, qualification rate parityequilibrium qualityHurt
Use DRL with scheduled disparity regularizationClassifier-population system · Long-term fairness experimentsfairness constraint violationsHurt
Use DRL with a true-positive plus 0.8 true-negative utilityClassifier-population system · Synthetic population, third disparity settingequilibrium qualityMixed

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