AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Blind Pareto Fairness and Subgroup Robustness

Natalia L Martinez, Martin A Bertran, Afroditi Papadaki, Miguel Rodrigues, Guillermo Sapiro

ICML 2021 · Learning theory and algorithms › Fairness · approach: Post-processing and transport for fairness · 3 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
Add Pareto efficiency constraint to minimax subgroup robustness (BPF vs DRO)BPF · UCI Adult, Law School, COMPAS, MIMIC-IIIlow-risk (best group) cross-entropy at equal worst-group riskImproved
Set minimum subgroup size rho small (e.g., 0.15-0.3) so worst-group cross-entropy approaches uniform classifier riskBPF and DRO · UCI Adultworst-group cross-entropyNo clear effect
Use high-capacity adversary network in ARL (ARL HC) versus standard ARL (ablation)ARL · UCI Adult, Law School, COMPAS, MIMIC-IIIworst-group cross-entropyMixed
Train BPF with smaller minimum partition size rho (ablation)BPF · UCI Adultaccuracy on low-risk demographic groupsHurt
BPF vs ARL/DRO on protected-attribute accuracy at same rhoBPF · UCI Adult, Table 1accuracy across demographic groupsImproved

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