Research map / Learning theory and algorithms / Clustering
Distributed $k$-Clustering for Data with Heavy Noise
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 local aggregation before sending data to the coordinator | Distributed (k, z)-center · (k, z)-center, general metrics | communication cost: O( km/ε + m log Δ/ε ) | Helped |
| Allow up to (1+ε)z outliers rather than 2z | Distributed (k, z)-center · (k, z)-center, general metrics | outlier factor: 2+ε -> 1+ε | Helped |
| Use coresets for discretized truncated-distance instances | Distributed (k, z)-median/means · (k, z)-median and (k, z)-means, Euclidean metrics | bicriteria approximation: (1+ε, 1+ε) | Helped |
| Increase ε to 0.99 instead of using ε=0.1 (ablation) | Distributed (k, z)-center algorithm · Small-dataset experiments, varying k | communication cost | Helped |
| Increase ε to 0.99 instead of using ε=0.1 (ablation) | Distributed (k, z)-center algorithm · Small-dataset experiments, varying k | objective value | Hurt |
Closest papers by meaning
- Fast Algorithms for Distributed k-Clustering with Outliers (ICML 2023 · similarity 0.95)
- A Practical Algorithm for Distributed Clustering and Outlier Detection (NeurIPS 2018 · similarity 0.91)
- Clustering What Matters: Optimal Approximation for Clustering with Outliers (AAAI 2023 · similarity 0.91)
- Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces (NeurIPS 2024 · similarity 0.89)
- Near-Linear Time Approximation Algorithms for k-means with Outliers (ICML 2024 · similarity 0.89)
- Fully-Scalable Massively Parallel Algorithm for k-center with Outliers (AAAI 2025 · similarity 0.88)
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.