Research map / Learning theory and algorithms / Fairness
Certifying Some Distributional Fairness with Subpopulation Decomposition
Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li
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 |
|---|---|---|---|
| add non-skewness box constraint (smaller Delta_s) on the shifted distribution Q (ablation) | fairness certificate (sensitive shifting) · Adult | certified error bound | Improved |
| add fairness constraint and the subpopulation-decomposition optimization versus WRM distributional robustness bound | fairness certificate · synthetic dataset | certified loss bound (JSD loss) | Improved |
| switch from sensitive shifting to general shifting (extra shift within each subpopulation) | fairness certificate · Adult, Compas, Health, Lawschool | certification tightness | Hurt |
| certify with sensitive shifting only (no change within subpopulations) | fairness certificate · Adult, Compas, Health, Lawschool, Crime, German | classification error and BCE loss | Improved |
| use very small distribution distance between P and Q with the fairness constraint | fairness certificate · synthetic dataset | feasibility of certificate | Hurt |
| use large distribution shift with the fairness constraint | fairness certificate · synthetic dataset | certified loss bound | Improved |
Closest papers by meaning
- Achievable Fairness on Your Data With Utility Guarantees (NeurIPS 2024 · similarity 0.87)
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings (NeurIPS 2026 · similarity 0.87)
- Optimal Fair Learning Robust to Adversarial Distribution Shift (ICML 2025 · similarity 0.87)
- Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective (ICML 2025 · similarity 0.87)
- On the Maximal Local Disparity of Fairness-Aware Classifiers (ICML 2024 · similarity 0.86)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.86)
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.
