Research map / Learning theory and algorithms / Prediction and decision losses
Improving Conditional Coverage via Orthogonal Quantile Regression
Shai Feldman, Stephen Bates, Yaniv Romano
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 |
|---|---|---|---|
| add decorrelation penalty (orthogonal QR) | vanilla QR · Synthetic two-group, low noise | minority coverage (%): 66.34 -> 82.55 | Improved |
| add decorrelation penalty (orthogonal QR) | vanilla QR · Synthetic two-group, high noise | minority coverage (%): 68.74 -> 83.74 | Improved |
| add decorrelation penalty (orthogonal QR) | vanilla QR · Synthetic two-group, low noise | Delta WSC improvement (%): -13.88 | Hurt |
| add decorrelation penalty (orthogonal QR) | vanilla QR · Synthetic two-group, high noise | Pearson correlation improvement (%): +72.21 | Improved |
| add decorrelation penalty (orthogonal QR) | vanilla QR · facebook_1 | coverage (%): 88.10 -> 90.48 | Improved |
| add decorrelation penalty (orthogonal QR) | vanilla QR · blog_data | coverage (%): 82.89 -> 88.92 | Improved |
| add decorrelation penalty (orthogonal QR) | vanilla QR · naval | coverage (%): 89.89 -> 89.50 | No clear effect |
| add decorrelation penalty (orthogonal QR) | vanilla QR · nine real datasets | Pearson correlation, HSIC: +27.54 to +91.27 | Improved |
| add decorrelation penalty (orthogonal QR) | vanilla QR · bio, naval | Delta WSC improvement (%): -44.73, -57.52 | Hurt |
| add decorrelation penalty (orthogonal QR) | vanilla QR · kin8nm, naval | Delta Node improvement (%): -16.44, -14.34 | Hurt |
| add decorrelation penalty (orthogonal QR) | vanilla QR · naval | interval length: 0.56 -> 1.49 | Hurt |
| conformalize intervals (COQR vs CQR) (ablation) | orthogonal QR · real data with conformalization | marginal coverage (%): 90.11 vs 90.08 | Improved |
Closest papers by meaning
- Understanding the Under-Coverage Bias in Uncertainty Estimation (NeurIPS 2021 · similarity 0.89)
- Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise (ICML 2024 · similarity 0.88)
- Rectifying Conformity Scores for Better Conditional Coverage (ICML 2025 · similarity 0.88)
- Probabilistic Conformal Prediction with Approximate Conditional Validity (ICLR 2025 · similarity 0.87)
- Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage (ICML 2025 · similarity 0.86)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.86)
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.
