Research map / Learning theory and algorithms / Sample complexity
Quantification Under Prior Probability Shift: the Ratio Estimator and its Extensions
Afonso Fernandes Vaz, Rafael Izbicki, Rafael Bassi Stern
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 ratio estimator instead of classify and count | quantification with LR, k-NN, RF classifiers · Candles, Bank, SPAM, Breast Cancer, Blocks | MSE of theta | Improved |
| use ratio estimator when theta is about 0.5 (no prior shift) | ratio estimator · Five quantification datasets, theta=0.5 | MSE of theta | No clear effect |
| use soft-classifier ratio estimator rather than hard-classifier variant | ratio estimator · Five quantification datasets | MSE of theta | Improved |
| choose random forest as the classifier g | ratio estimator · Five quantification datasets | MSE of theta | Improved |
| use RKHS ratio estimator with Gaussian kernel instead of linear kernel | ratio estimator · Five quantification datasets | MSE of theta | Improved |
| compare ratio estimator with EM methods | ratio estimator · Five quantification datasets (e.g. bank) | MSE of theta | Mixed |
| project the raw multiclass ratio estimator onto the simplex | multiclass ratio estimator · Simulated 3-class Gaussian | MSE | Improved |
| use regression ratio estimator instead of classify and count when classes overlap (small mu) | regression quantification · Simulated, mu in {0.5,1,1.5,2}, k in {1,2} | MSE of theta(z) | Improved |
| use regression ratio estimator for large mu (easy classification) | regression quantification · Simulated, large mu | MSE of theta(z) | No clear effect |
Closest papers by meaning
- Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift (ICLR 2025 · similarity 0.85)
- Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift (NeurIPS 2024 · similarity 0.84)
- Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias (NeurIPS 2026 · similarity 0.84)
- Learning from Noisy Labels via Conditional Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.84)
- Quantifying Uncertainty in the Presence of Distribution Shifts (NeurIPS 2025 · similarity 0.84)
- Not all distributional shifts are equal: Fine-grained robust conformal inference (ICML 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.
