Research map / Learning theory and algorithms / Clustering
Fast Algorithms for Distributed k-Clustering with Outliers
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 |
|---|---|---|---|
| Space-narrowing sampling (ours 0.99) vs dist_kzc 0.99 on communication cost | distributed (k,z)-center · gas, Higgs, covertype datasets, varying k | communication cost: reduced by at least 30% | Helped |
| Space-narrowing sampling (ours 0.99) vs dist_kzc 0.99 on running time | distributed (k,z)-center · Higgs, varying k | running time: more than 26 times faster | Helped |
| Space-narrowing sampling with ϵ=0.99 on clustering radius | distributed (k,z)-center · large datasets, varying k | clustering radius | No clear effect |
| Space-narrowing sampling (ours 0.99) on SIFT running time | distributed (k,z)-center · SIFT (100M x 128) | running time: other algorithms need at least 48 hours; ours within 2 hours | Helped |
| Space-narrowing sampling (ours 0.99) vs dist_kzc on communication cost averaged over datasets | distributed (k,z)-center · five datasets, varying k | communication cost: reduced by 48% on average | Helped |
| Using ϵ=0.1 instead of 0.99 in space-narrowing sampling (ablation) | distributed (k,z)-center · large datasets | communication cost and running time | No clear effect |
Closest papers by meaning
- Distributed $k$-Clustering for Data with Heavy Noise (NeurIPS 2018 · similarity 0.95)
- Near-Linear Time Approximation Algorithms for k-means with Outliers (ICML 2024 · similarity 0.92)
- A Practical Algorithm for Distributed Clustering and Outlier Detection (NeurIPS 2018 · similarity 0.92)
- A More Efficient Reduction from Outlier-Aware to Outlier-Free k-Median (AAAI 2026 · similarity 0.91)
- Fully-Scalable Massively Parallel Algorithm for k-center with Outliers (AAAI 2025 · similarity 0.90)
- Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces (NeurIPS 2024 · 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.