Research map / Learning theory and algorithms / Fairness
Robust Optimization for Fairness with Noisy Protected Groups
Serena Wang, Wenshuo Guo, Harikrishna Narasimhan, Andrew Cotter, Maya Gupta, Michael I. Jordan
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 |
|---|---|---|---|
| Use robust approaches (DRO or soft group assignments) instead of naive noisy-group constraints | Fairness-constrained hinge-loss classifier · Adult and Credit, noise 0.1-0.5 | max true-group constraint violation | Improved |
| Use robust approaches instead of naive approach | Fairness-constrained classifier · Adult and Credit | error rate | Hurt |
| Use soft group assignments instead of DRO | Robust constrained classifier · Adult and Credit | error rate | Improved |
| Add fairness constraints using true groups | Unconstrained classifier · Adult | max true-group constraint violation: 0.0234 -> -0.0469 | Improved |
| Add fairness constraints using true groups | Unconstrained classifier · Credit | error rate: 0.1797 -> 0.1796 | No clear effect |
Closest papers by meaning
- Preserving AUC Fairness in Learning with Noisy Protected Groups (ICML 2025 · similarity 0.90)
- Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization (ICLR 2023 · similarity 0.89)
- Group-Aware Threshold Adaptation for Fair Classification (AAAI 2022 · similarity 0.89)
- Noise-tolerant fair classification (NeurIPS 2019 · similarity 0.89)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.88)
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness (NeurIPS 2025 · similarity 0.88)
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.
