Research map / Time series / Causal and generative time series
Conformal Prediction for Time Series
Chen Xu, Yao Xie
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 EnbPI instead of QOOB | conformal prediction · Atlanta solar, train ratio 0.10 | coverage: 0.684 -> 0.893 | Improved |
| use EnbPI instead of ICP | conformal prediction · Atlanta solar, train ratio 0.10 | coverage: 0.646 -> 0.893 | Improved |
| use EnbPI instead of AdaptCI | conformal prediction · Atlanta solar, train ratio 0.10 | coverage: 0.828 -> 0.893 | Improved |
| use EnbPI instead of AdaptCI | conformal prediction · Atlanta solar, train ratio 0.28 | coverage: 0.909 -> 0.905 | No clear effect |
| use EnbPI instead of J+aB | conformal prediction · Atlanta solar, train ratio 0.10 | interval width: 116.129 -> 204.597 | Hurt |
| increase training ratio from 0.10 to 0.28 | EnbPI · Atlanta solar | coverage: 0.893 -> 0.905 | Improved |
| increase training ratio from 0.10 to 0.28 | QOOB · Atlanta solar | coverage: 0.684 -> 0.850 | Improved |
| use EnbPI instead of ARIMA | time-series methods · Atlanta solar, alpha=0.10 | coverage: 0.784 -> 0.896 | Improved |
| use EnbPI instead of Exponential Smoothing | time-series methods · Atlanta solar, alpha=0.10 | interval width: 313.185 -> 216.989 | Improved |
| use RNN or NN instead of Ridge as EnbPI predictor | EnbPI · traffic anomaly detection sensor 282 | F1: 0.13 -> 0.88 | Improved |
| use EnbPI RNN instead of OCSVM | anomaly detectors · traffic anomaly detection sensor 282 | F1: 0.51 -> 0.88 | Improved |
| use EnbPI RNN instead of OCSVM | anomaly detectors · traffic anomaly detection sensor 235 | F1: 0.45 -> 0.77 | Improved |
Closest papers by meaning
- Conformal prediction for multi-dimensional time series by ellipsoidal sets (ICML 2024 · similarity 0.89)
- Probabilistic Conformal Prediction with Approximate Conditional Validity (ICLR 2025 · similarity 0.87)
- Kernel-based Optimally Weighted Conformal Time-Series Prediction (ICLR 2025 · similarity 0.87)
- Error-quantified Conformal Inference for Time Series (ICLR 2025 · similarity 0.87)
- Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations (NeurIPS 2025 · similarity 0.86)
- Backward Conformal Prediction (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.
