Research map / Learning theory and algorithms / Clustering
Wasserstein $K$-means for clustering probability distributions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 pairwise Wasserstein distances with the SDP relaxation instead of barycenter-based assignment | Wasserstein K-means · Counterexample simulation, n=101 | exact recovery rate: 0.40 -> 1.00 | Helped |
| Use pairwise Wasserstein distances with the SDP relaxation instead of barycenter-based assignment | Wasserstein K-means · Counterexample simulation, n=202 | exact recovery rate: 0.34 -> 1.00 | Helped |
| Use pairwise Wasserstein distances with the SDP relaxation instead of barycenter-based assignment | Wasserstein K-means · Counterexample simulation, n=303 | exact recovery rate: 0.46 -> 1.00 | Helped |
| Use pairwise Wasserstein distances with SDP rather than barycenters | Wasserstein K-means · MNIST₁ | error rate: 0.310 (0.069) -> 0.235 (0.045) | Helped |
| Use pairwise Wasserstein distances without SDP rather than barycenters | Wasserstein K-means · MNIST₁ | error rate: 0.310 (0.069) -> 0.156 (0.057) | Helped |
| Use pairwise Wasserstein distances with SDP rather than barycenters | Wasserstein K-means · MNIST₂ | error rate: 0.324 (0.032) -> 0.279 (0.050) | Helped |
| Use pairwise Wasserstein distances without SDP rather than barycenters | Wasserstein K-means · MNIST₂ | error rate: 0.324 (0.032) -> 0.185 (0.097) | Helped |
| Use pairwise Wasserstein distances with SDP rather than barycenters | Wasserstein K-means · Fashion-MNIST | error rate: 0.141 (0.059) -> 0.082 (0.020) | Helped |
| Use pairwise Wasserstein distances without SDP rather than barycenters | Wasserstein K-means · Fashion-MNIST | error rate: 0.141 (0.059) -> 0.056 (0.014) | Helped |
| Use pairwise Wasserstein distances with SDP rather than barycenters | Wasserstein K-means · USPS handwriting | error rate: 0.240 (0.045) -> 0.206 (0.020) | Helped |
| Use pairwise Wasserstein distances without SDP rather than barycenters | Wasserstein K-means · USPS handwriting | error rate: 0.240 (0.045) -> 0.159 (0.061) | Helped |
| Use pairwise Wasserstein distances instead of barycenter-based clustering | Wasserstein K-means · MNIST₁ | F1 score: 0.698 (0.067) -> 0.842 (0.056) | Helped |
Closest papers by meaning
- Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems (ICLR 2025 · similarity 0.88)
- Multilevel Clustering via Wasserstein Means (ICML 2017 · similarity 0.88)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.87)
- Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness (ICML 2025 · similarity 0.86)
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (ICML 2024 · similarity 0.85)
- Fast unsupervised ground metric learning with tree-Wasserstein distance (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.