Research map / Label-efficient and robust learning / Domain adaptation and generalization
An Equivalence Analysis of Binary Quantification Methods
Alberto Castaño, Jaime Alonso, Pablo González, Juan José del Coz
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 |
|---|---|---|---|
| Represent each distribution with multiple quantile-group average probabilities instead of a single average (ablation) | PAC, yielding QUANTy · Synthetic data | AE: .0622 -> .0606 | Improved |
| Represent each distribution with multiple histogram bins instead of two bins (ablation) | AC, yielding HDy · Synthetic data (n+=50, n−=50, m=50) | AE: .0718 -> .0623 | Improved |
| Use multiple quantile groups rather than one average probability (ablation) | PAC / QUANTy · Benchmark datasets | AE | Improved |
| Use multiple histogram bins rather than AC's two-bin representation (ablation) | AC / HDy · Benchmark datasets | AE | Mixed |
| Increase the number of quantiles (ablation) | QUANTy · Synthetic data | AE | Improved |
| Increase the number of histogram bins (ablation) | HDy · Synthetic data | AE | Hurt |
| Increase the number of histogram bins (ablation) | CDFy · Synthetic data | AE | Improved |
| Increase the number of quantiles (ablation) | QUANTy · Synthetic data | prediction time | Hurt |
| Use SORD's EMD-based optimization rather than CDFy's L1-CDF optimization (ablation) | Binary quantification · UCI benchmark datasets | AE | No clear effect |
| Increase training and testing set sizes (ablation) | All evaluated quantifiers · Synthetic data | AE | Improved |
Closest papers by meaning
- A Comparative Evaluation of Quantification Methods (JMLR 2025 · similarity 0.88)
- DyS: A Framework for Mixture Models in Quantification (AAAI 2019 · similarity 0.85)
- Quantification Under Prior Probability Shift: the Ratio Estimator and its Extensions (JMLR 2019 · similarity 0.82)
- Bi-Level Alignment for Cross-Domain Crowd Counting (CVPR 2022 · similarity 0.82)
- quanda: An Interpretability Toolkit for Training Data Attribution Evaluation (NeurIPS 2026 · similarity 0.81)
- Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification (AAAI 2024 · similarity 0.80)
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.
