Research map / Learning theory and algorithms / Fairness
Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
Songkai Xue, Yuekai Sun, Mikhail Yurochkin
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 |
|---|---|---|---|
| solve calibrated problem with radius rho instead of plain sample average approximation (SAA) | constrained stochastic optimization (fair logistic regression) · Adult, epsilon-DP | test-time constraint satisfaction frequency | Improved |
| raise nominal satisfaction probability from SAA baseline to 95% | calibrated fair classifier · Adult, epsilon-DP | classification error rate: 2\% increase | Hurt |
| increase sample size n | calibrated newsvendor solution · multi-item newsvendor, 1000 replicates | constraint satisfaction frequency vs limiting probability | Improved |
Closest papers by meaning
- Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints (ICML 2019 · similarity 0.88)
- Too Relaxed to Be Fair (ICML 2020 · similarity 0.87)
- Learning with Statistical Equality Constraints (NeurIPS 2025 · similarity 0.86)
- Near-Optimal Solutions of Constrained Learning Problems (ICLR 2024 · similarity 0.84)
- Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective (ICML 2025 · similarity 0.83)
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings (NeurIPS 2026 · similarity 0.83)
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.
