Research map / Time series / Causal and generative time series
Coresets for Time Series Clustering
Lingxiao Huang, K. Sudhir, Nisheeth K Vishnoi
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 time-series coreset instead of uniform sampling, eps=0.5 | GMM time-series clustering · Synthetic 1 | V*_S: 3304 -> 2383 | Improved |
| Use time-series coreset instead of LFKF static coreset, eps=0.5 | GMM time-series clustering · Synthetic 1 | V*_S: 3461 -> 2383 | Improved |
| Use coreset instead of uniform sampling, eps=0.1 | GMM time-series clustering · Synthetic 1 | V*_S: 2058 -> 2050 | Improved |
| Use coreset instead of uniform sampling, eps=0.5 | GMM time-series clustering · Synthetic 2 | V*_S: 1361 -> 910 | Improved |
| Use coreset instead of LFKF, eps=0.4 | GMM time-series clustering · Synthetic 2 | V*_S: 1114 -> 860 | Improved |
| Use coreset instead of uniform sampling at eps=0.4 | GMM time-series clustering · Synthetic 1 | computation time T_C+T_S (s): 621 -> 38 | Improved |
| Use coreset instead of full data, eps=0.1 | GMM time-series clustering · Synthetic 2 | computation time (s): 9787 -> 694 | Improved |
| Coreset vs uniform sampling at fewer sampled pairs | GMM time-series clustering · Synthetic 1 | likelihood ratio gamma_S: 714 -> 684 | Improved |
| Increase error parameter eps from 0.1 to 0.5 | Coreset · Synthetic 1 | V*_S: 2050 -> 2383 | Hurt |
| Increase error parameter eps from 0.1 to 0.5 | Uniform sampling · Synthetic 1 | V*_S: 2058 -> 3304 | Hurt |
| Use dataset with more observations per entity (Synthetic 2 vs 1) | Coreset · Synthetic 2 | V*_S: 2383 -> 910 | Improved |
| Coreset at eps=0.3 versus LFKF | GMM time-series clustering · Synthetic 1 | V*_S: 2384 -> 2194 | Improved |
Closest papers by meaning
- Training Gaussian Mixture Models at Scale via Coresets (JMLR 2018 · similarity 0.90)
- Coresets for Clustering Under Stochastic Noise (NeurIPS 2025 · similarity 0.89)
- Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling (NeurIPS 2026 · similarity 0.87)
- Consistent Algorithms for Clustering Time Series (JMLR 2016 · similarity 0.86)
- Universal Weak Coreset (AAAI 2024 · similarity 0.85)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (NeurIPS 2024 · similarity 0.84)
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.
