Research map / Learning theory and algorithms / Fairness
Ensuring Fairness Beyond the Training Data
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 |
|---|---|---|---|
| enforce fairness over all reweightings within l1 distance epsilon (robust fair classifier vs standard fair classifiers) | fair logistic regression · Adult, Communities and Crime, Law School, COMPAS | fairness violation (DP and EO) under reweighted test distributions | Helped |
| enforce robust fairness (robust fair classifier vs others) | fair logistic regression · all four datasets | unweighted test accuracy: drops by at most 5%-10% | Hurt |
| enforce robust fairness (robust fair classifier vs others) | fair logistic regression · COMPAS | fairness violation on original test set: at most 12% | Hurt |
Closest papers by meaning
- Optimal Fair Learning Robust to Adversarial Distribution Shift (ICML 2025 · similarity 0.92)
- An Efficient Geometric Characterization of Robust Fair Learning (NeurIPS 2026 · similarity 0.91)
- Fair Classification with Adversarial Perturbations (NeurIPS 2021 · similarity 0.91)
- Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees (ICML 2021 · similarity 0.91)
- fairret: a Framework for Differentiable Fairness Regularization Terms (ICLR 2024 · similarity 0.89)
- Achievable Fairness on Your Data With Utility Guarantees (NeurIPS 2024 · 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.