Research map / Learning theory and algorithms / Prediction and decision losses
The Statistical Scope of Multicalibration
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 |
|---|---|---|---|
| Require the target property Γ to be elicitable (equivalently convex level sets / identifiable) for it to be sensible for calibration and multicalibratable | continuous scalar distributional properties · theoretical characterization (batch) | multicalibratability (sensibility for calibration) | Helped |
| Jointly multicalibrate a non-elicitable property Γ1 (e.g. variance) with an elicitable Γ0 (e.g. mean) using Algorithm 2 instead of multicalibrating Γ1 alone | conditionally elicitable properties (Bayes pairs, mean-moment) · theoretical guarantee (batch) | joint multicalibration error | Helped |
| Apply distortion risk measures (other than means and quantiles) as multicalibration targets | distortion risk measures · theoretical impossibility on finite-support distributions | sensibility for calibration | Hurt |
| Multicalibrate CVaR alone instead of jointly with quantile | CVaR (expected shortfall) · theoretical (batch) | sensibility for calibration | Hurt |
Closest papers by meaning
- Instance-Adaptive Online Multicalibration (NeurIPS 2026 · similarity 0.87)
- Improved and Oracle-Efficient Online $\ell_1$-Multicalibration (ICML 2025 · similarity 0.87)
- Discretization-free Multicalibration through Loss Minimization over Tree Ensembles (NeurIPS 2025 · similarity 0.85)
- Improved Bounds for Swap Multicalibration and Swap Omniprediction (NeurIPS 2025 · similarity 0.85)
- Testing Calibration in Nearly-Linear Time (NeurIPS 2024 · similarity 0.84)
- Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift (NeurIPS 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.