Research map / Learning theory and algorithms / Prediction and decision losses
Adaptive Sampling for Minimax Fair Classification
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 |
|---|---|---|---|
| Adaptively allocate samples using optimistic upper confidence bounds | Fair classification on UTKFace · UTKFace | minimum test accuracy | Helped |
| Adaptively allocate samples rather than sampling uniformly | Fair classification on FashionMNIST · FashionMNIST | worst-case accuracy | Helped |
| Use adaptive sampling instead of Uniform sampling | Fair classification on Adult · Adult | minimum test accuracy at small sample sizes | Helped |
| Include a trend-based Mann-Kendall term in the UCB (ablation) | Adaptive sampling on SyntheticModel2 · SyntheticModel2, attribute v | average accuracy: 4 points higher | Helped |
| Remove the trend-based Mann-Kendall term from the UCB (ablation) | Adaptive sampling on SyntheticModel2 · SyntheticModel2, attribute v | average accuracy: 4 points | Hurt |
| Add an exploration component rather than acting greedily | Adaptive sampling on SyntheticModel1 · SyntheticModel1 | convergence to the optimal mixture | Helped |
| Use greedy sampling with epsilon=0 instead of exploration (ablation) | Adaptive sampling on SyntheticModel1 · SyntheticModel1 | convergence to the optimal mixture | Hurt |
Closest papers by meaning
- Active Sampling for Min-Max Fairness (ICML 2022 · similarity 0.89)
- Scalable and Stable Surrogates for Flexible Classifiers with Fairness Constraints (NeurIPS 2021 · similarity 0.87)
- Optimal Fair Learning Robust to Adversarial Distribution Shift (ICML 2025 · similarity 0.85)
- Learning with Statistical Equality Constraints (NeurIPS 2025 · similarity 0.85)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.85)
- Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective (AAAI 2024 · similarity 0.85)
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.