Research map / Learning theory and algorithms / Fairness
Meritocratic Fairness for Cross-Population Selection
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 |
|---|---|---|---|
| Use FAIRTOP (noisy top-k on normalized empirical CCDF scores) instead of deterministic greedy top-k by empirical CDF | cross-population selection · Simulation (m1=100, m2=50) | unfairness ratio / fairness | Helped |
| Increase epsilon in FAIRTOP to reduce regret at the cost of weaker fairness (ablation) | FAIRTOP · Simulation regret vs population size | regret | Helped |
| Impose exact ex-interim fairness constraint (instead of approximate) | selection algorithms · Theoretical lower bound (Theorem 5.1) | regret | Hurt |
| Grow population sizes in fixed ratio (regret of FAIRTOP) | FAIRTOP · Simulation / Corollary 3.8 | regret | Helped |
| Use a learned parametric model (normal CDF from estimated means) instead of FAIRTOP | cross-population selection · Simulation with non-normal population 2 scores | fairness | Hurt |
Closest papers by meaning
- Group Meritocratic Fairness in Linear Contextual Bandits (NeurIPS 2022 · similarity 0.88)
- Centralized Selection with Preferences in the Presence of Biases (ICML 2024 · similarity 0.88)
- Fairness in Matching under Uncertainty (ICML 2023 · similarity 0.87)
- Learning Fair Policies for Multi-Stage Selection Problems from Observational Data (AAAI 2024 · similarity 0.86)
- Smooth Partial Lotteries for Stable Randomized Selection (NeurIPS 2026 · similarity 0.85)
- Promoting Fairness Among Dynamic Agents in Online-Matching Markets under Known Stationary Arrival Distributions (NeurIPS 2024 · similarity 0.84)
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.