Research map / Learning theory and algorithms / Prediction and decision losses
Fast Conformal Prediction Using Conditional Interquantile Intervals
Naixin Guo, Rui Luo, Zhixin Zhou
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 CIR instead of CQR on skewed data | conformal regression with deep quantile model · Synthetic (|I|=5000, skew 2.7) | interval width: 5.345 -> 3.776 | Improved |
| add width-based selection rule (CIR+ vs CIR) (ablation) | CIR · Synthetic (|I|=5000, skew 2.7) | interval width: 3.776 -> 3.643 | Improved |
| add width-based selection rule (CIR+ vs CIR) (ablation) | CIR · Synthetic (|I|=5000, skew 2.7) | time: 0.663 -> 0.862 | Hurt |
| replace histogram construction of CHR with interquantile intervals (CIR) | CHR · Synthetic (|I|=5000, skew 2.7) | time: 103.637 -> 0.663 | Improved |
| replace histogram construction of CHR with interquantile intervals (CIR) | CHR · Synthetic (|I|=5000, skew 2.7) | interval width: 3.389 -> 3.776 | Hurt |
| increase sample size | CHR · Synthetic (skew 2.7) | time: 36.597 (|I|=500) -> 103.637 (|I|=5000) | Hurt |
| increase distribution symmetry (skew 2.70 to 0.66) | CIR and CQR vs CHR · Synthetic (|I|=5000) | interval width: CQR minus CIR+ gap: 5.345 vs 3.643 at skew 2.70; 5.950 vs 5.715 at skew 0.66 | Mixed |
| use CIR with small calibration/training data | CIR/CIR+ · Synthetic (|I|=500) | interval width: 3.930 (|I|=500) vs 3.776 (|I|=5000) | Hurt |
| CIR+ vs CIR marginal coverage tie handling (ablation) | CIR · Synthetic (|I|=5000, skew 2.7) | marginal coverage: 0.905 -> 0.900 | Improved |
Closest papers by meaning
- Co-optimization for Adaptive Conformal Prediction (NeurIPS 2026 · similarity 0.90)
- Conformal Thresholded Intervals for Efficient Regression (AAAI 2025 · similarity 0.89)
- Rectifying Conformity Scores for Better Conditional Coverage (ICML 2025 · similarity 0.88)
- Probabilistic Conformal Prediction with Approximate Conditional Validity (ICLR 2025 · similarity 0.88)
- A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression (ICML 2025 · similarity 0.88)
- Optimal transport-based conformal prediction (ICML 2025 · similarity 0.88)
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.
