Research map / Learning theory and algorithms / Fairness

Fairness in limited resource prediction-driven decisions

NeurIPS 2026 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies fairness in prediction-driven resource allocation under capacity constraints, connecting classical algorithmic fairness notions with resource allocation.

Problem

Prediction-driven allocation of scarce resources under strict capacity constraints can produce highly unbalanced outcomes across populations because of information gaps between them.

Approach

Connects classical algorithmic fairness notions with resource allocation under capacity constraints to analyze prediction-driven allocation through a fairness lens. Full method details unavailable from the abstract provided.

Closest papers by meaning

• Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized (ICML 2024 · similarity 0.90)
• Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty (NeurIPS 2024 · similarity 0.88)
• Fairness under Competition (NeurIPS 2025 · similarity 0.88)
• A Comprehensive View of Fairness through Distributional Stability (NeurIPS 2026 · similarity 0.88)
• Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis (NeurIPS 2025 · similarity 0.88)
• Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective (ICML 2025 · similarity 0.87)