Research map / Learning theory and algorithms / Fairness
Fairness Without Demographics in Repeated Loss Minimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace ERM with chi-square DRO | Logistic regression · Simulated classification over repeated rounds | minority accuracy stability | Helped |
| Replace ERM with chi-square DRO | Logistic regression · Simulated classification, minority fraction as low as 1% | minority accuracy: 75% | Helped |
| Replace ERM with chi-square DRO | Bigram autocomplete · Autocomplete, minority users | user satisfaction: 3.7 -> 4.0 | Helped |
| Replace ERM with chi-square DRO | Bigram autocomplete · Autocomplete, minority users | retention: 0.7 -> 0.85 | Helped |
| Replace ERM with chi-square DRO | Bigram autocomplete · Autocomplete, SAE users | user satisfaction | Hurt |
| Use choices of αmin below 0.5 instead of αmin = 0.2 (ablation) | DRO logistic regression · Simulated classification | disparity amplification | No clear effect |
Closest papers by meaning
- Towards Harmless Rawlsian Fairness Regardless of Demographic Prior (NeurIPS 2024 · similarity 0.88)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.87)
- On Optimal Steering to Achieve Exact Fairness (NeurIPS 2025 · similarity 0.87)
- When majority rules, minority loses: bias amplification of gradient descent (NeurIPS 2025 · similarity 0.87)
- Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference (NeurIPS 2025 · similarity 0.86)
- Subgroups Matter for Robust Bias Mitigation (ICML 2025 · 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.