Research map / Learning theory and algorithms / Fairness
Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making
Hoda Heidari, Claudio Ferrari, Krishna Gummadi, Andreas Krause
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · COMPAS and Crime and Communities | prediction accuracy | Hurt |
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · COMPAS and Crime and Communities | inequality (Atkinson index) | Improved |
| Use a smaller risk-aversion parameter α | Welfare-constrained learning · COMPAS and Crime and Communities | inequality | Improved |
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · COMPAS | false negative rate difference | Improved |
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · Crime and Communities | positive residual difference | Mixed |
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · COMPAS | average violation of pairwise individual-fairness constraints | Improved |
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · Crime and Communities | average violation of pairwise individual-fairness constraints | Mixed |
| Increase the minimum social-welfare threshold τ | Welfare-constrained learning · COMPAS and Crime and Communities | false positive and false negative rate differences | Improved |
Closest papers by meaning
- Fairness in limited resource prediction-driven decisions (NeurIPS 2026 · similarity 0.89)
- On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning (ICML 2019 · similarity 0.89)
- From Parity to Preference-based Notions of Fairness in Classification (NeurIPS 2017 · similarity 0.89)
- Fairness Shields: Safeguarding against Biased Decision Makers (AAAI 2025 · similarity 0.89)
- Fair Participation via Sequential Policies (AAAI 2024 · similarity 0.87)
- Fairness-Accuracy Trade-Offs: A Causal Perspective (AAAI 2025 · similarity 0.87)
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.
