Research map / Time series / Causal and generative time series
ResCP: Reservoir Conformal Prediction for Time Series Forecasting
Roberto Neglia, Andrea Cini, Michael M. Bronstein, Filippo Maria Bianchi
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 time-dependent decay weights (ablation) | ResCP · Exchange (RNN) | Winkler score: 0.0269 -> 0.0264 | Improved |
| add time-dependent decay weights (ablation) | ResCP · Beijing (RNN) | Winkler score: 114.85 -> 106.07 | Improved |
| add time-dependent decay weights (ablation) | ResCP · Solar (RNN) | Winkler score: 107.46 -> 104.24 | Improved |
| add time-dependent decay weights (ablation) | ResCP · ACEA (RNN) | Winkler score: 13.41 -> 12.91 | Improved |
| use sliding calibration window (ablation) | ResCP · Exchange (RNN) | Winkler score: 0.0284 -> 0.0264 | Improved |
| use sliding calibration window (ablation) | ResCP · ACEA (RNN) | Winkler score: 14.80 -> 12.91 | Improved |
| use sliding calibration window (ablation) | ResCP · Beijing (RNN) | Winkler score: 106.07 -> 97.99 | Hurt |
| use sliding calibration window (ablation) | ResCP · Solar (RNN) | Winkler score: 104.70 -> 104.24 | No clear effect |
| replace learned attention weights (HopCPT) with untrained reservoir similarity | ResCP · Solar/Beijing/Exchange/ACEA | Winkler score: 112.46 -> 104.24 | Improved |
| use reservoir-weighted residuals instead of uniform weights (SCP) | ResCP · Solar (RNN) | Winkler score: 171.41 -> 104.24 | Improved |
| train a quantile-regression readout on reservoir states instead of similarity weighting | ResCQR · ACEA (RNN) | Winkler score: 12.91 -> 34.61 | Hurt |
| train a GRU quantile model (CoRNN) instead of untrained reservoir | CoRNN · Solar (RNN) | Winkler score: 104.24 -> 78.42 | Improved |
Closest papers by meaning
- Neural Conformal Control for Time Series Forecasting (AAAI 2025 · similarity 0.87)
- Kernel-based Optimally Weighted Conformal Time-Series Prediction (ICLR 2025 · similarity 0.86)
- Co-optimization for Adaptive Conformal Prediction (NeurIPS 2026 · similarity 0.85)
- Conformal Prediction for Time-series Forecasting with Change Points (NeurIPS 2025 · similarity 0.85)
- Flow-Based Conformal Predictive Distributions (NeurIPS 2026 · similarity 0.85)
- Error-quantified Conformal Inference for Time Series (ICLR 2025 · similarity 0.85)
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.
