Research map / Time series / Foundation models for time series
Ranking Time Series using a Time Warping Ideal Point Model
Lucas Zoroddu, Pierre Humbert, Laurent Oudre
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 DTW distance instead of L2 under strong warping | IPM · Synthetic noise-level ranking (warp 3, n=2000) | Kendall tau: 0.25 -> 0.73 | Improved |
| use TWED distance instead of L2 under strong warping | IPM · Synthetic noise-level ranking (warp 3, n=2000) | Kendall tau: 0.25 -> 0.68 | Improved |
| use TWED distance instead of L2 without warping | IPM · Synthetic noise-level ranking (warp 0, n=2000) | Kendall tau: 0.83 -> 0.83 | No clear effect |
| use TWED instead of L2 at small sample size without warping | IPM · Synthetic noise-level ranking (warp 0, n=50) | Kendall tau: 0.37 -> 0.76 | Improved |
| use DTW distance instead of L2 | IPM · Basic Motions | Kendall tau: 0.42 -> 0.69 | Improved |
| use TWED distance instead of L2 | IPM · Basic Motions | Kendall tau: 0.42 -> 0.70 | Improved |
| increase training samples from 50 to 2000 with DTW | IPM with DTW · Synthetic noise-level ranking (warp 0) | Kendall tau: 0.65 -> 0.85 | Improved |
| use TWED instead of DTW under strong warping | IPM · Synthetic noise-level ranking (warp 3, n=50) | Kendall tau: 0.41 -> 0.54 | Improved |
| use Catch22 features before L2 distance | IPM with L2 · Basic Motions | Kendall tau: 0.42 -> 0.27 | Hurt |
| increase ROCKET kernels from 200 to 1000 with RankSVM | RankSVM · Basic Motions | Kendall tau: 0.65 -> 0.83 | Improved |
| use TWED instead of best feature baseline (RankSVM Rocket 1000) | IPM with TWED · Basic Motions | Kendall tau: 0.83 -> 0.70 | Hurt |
Closest papers by meaning
- TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning (ICML 2025 · similarity 0.86)
- Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning (AAAI 2025 · similarity 0.83)
- ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models (NeurIPS 2025 · similarity 0.83)
- TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation (ICML 2025 · similarity 0.83)
- InteDisUX: Intepretation-Guided Discriminative User-Centric Explanation for Time Series (AAAI 2025 · similarity 0.83)
- JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract) (AAAI 2024 · similarity 0.83)
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.
