AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Pushing the limits of fairness impossibility: Who's the fairest of them all?

Brian Hsu, Rahul Mazumder, Preetam Nandy, Kinjal Basu

NeurIPS 2022 · Learning theory and algorithms › Fairness · approach: Fair allocation and selection · 1 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
solve with MILP reformulation instead of interior-point on the QCQPMFOpt · ACS Coverageoptimality gap (%): 79.711 ± 0.782 -> 7.878 ± 2.207Improved
solve with MILP reformulation instead of interior-point on the QCQPMFOpt · COMPASoptimality gap (%): 62.88 ± 13.407 -> 17.055 ± 7.482Improved
solve with MILP reformulation instead of interior-point on the QCQPMFOpt · Heart Diseaseoptimality gap (%): 26.385 ± 17.401 -> 3.81 ± 0.864Improved
solve with MILP reformulation instead of interior-point on the QCQPMFOpt · ACS Incomeoptimality gap (%): 15.076 ± 6.461 -> 10.621 ± 3.402Improved
solve with MILP reformulation instead of interior-point on the QCQPMFOpt · ACS Traveloptimality gap (%): 2.554 ± 0.254 -> 2.242 ± 0.28No clear effect
solve with MILP instead of interior-pointMFOpt · ACS CoverageAUC: 0.5420 -> 0.8149Improved
solve with MILP instead of interior-pointMFOpt · COMPASAUC: 0.5143 -> 0.7378Improved
solve with MILP instead of interior-pointMFOpt · ACS IncomeAUC: 0.9041 -> 0.9044No clear effect
apply MFOpt post-processing versus Rezaei in-processing methodrandom forest · Comparison with Rezaei, testAUC: 0.6619 -> 0.747Improved
apply MFOpt post-processing versus Rezaei in-processing methodrandom forest · Comparison with Rezaei, testepsilon_EOdds: 0.0291 -> 0.0167Improved
apply MFOpt post-processing versus Rezaei in-processing methodrandom forest · Comparison with Rezaei, testepsilon_PRP: 0.1091 -> 0.0986No clear effect
apply MFOpt versus Pleiss post-processingrandom forest · Comparison with Pleiss, testepsilon_PRP: 0.4147 -> 0.1547Improved

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