Research map / Label-efficient and robust learning / Recognition and long-tail
DyS: A Framework for Mixture Models in Quantification
André Maletzke, Denis dos Reis, Everton Cherman, Gustavo Batista
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 |
|---|---|---|---|
| use fewer histogram bins (up to about 20) instead of 10-110 bins (ablation) | DyS with histogram distances (Topsøe, Hellinger) · 24 binary datasets | MAE: HD: 95% of best results within 2 to 14 bins | Improved |
| increase test sample size (ablation) | DyS · 24 binary datasets | MAE | Improved |
| replace Hellinger distance with Topsøe (tuned bins) (ablation) | DyS / HDy · 24 binary datasets | quantification rank / MAE | Improved |
| use parameter-free SORD instead of Hellinger (HDy) (ablation) | DyS · 24 binary datasets | quantification error | Improved |
| use Cosine, Harmonic Mean, Kumar-Hassebrook or Inner Product distances (ablation) | DyS · 24 binary datasets | MAE: errors greater than 70% on average | Hurt |
| use ORD distance (insensitive to number of bins) (ablation) | DyS · 24 binary datasets | quantification error | Mixed |
Closest papers by meaning
- A Comparative Evaluation of Quantification Methods (JMLR 2025 · similarity 0.90)
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework (NeurIPS 2025 · similarity 0.85)
- Scaling Laws for Optimal Data Mixtures (NeurIPS 2025 · similarity 0.84)
- Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance (ICML 2024 · similarity 0.84)
- Classification Diffusion Models: Revitalizing Density Ratio Estimation (NeurIPS 2024 · similarity 0.84)
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives (NeurIPS 2026 · 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.
