Research map / Learning theory and algorithms / Clustering
Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances
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 exact dynamic programming (Algorithm 5) instead of approximate DP over discretized costs (Algorithm 6) on synthetic data (ablation) | k-means clustering on perturbation-resilient synthetic data · Synthetic n=10^5, d=100 | running time (seconds) vs k | Mixed |
| Replace theoretical optimal LSH with Datar et al. p-stable LSH (r=4, m=10, t=100) | near neighbor graph construction · Synthetic and real datasets | k-means cost ratio | No clear effect |
| Run the proposed algorithm on real datasets that are not perturbation resilient | Algorithm 6 vs k-means++ · Real datasets (8 UCI/OpenML sets) | k-means cost ratio vs k-means++: ratios 1.19 to 1.64 | Hurt |
Closest papers by meaning
- Clustering Stable Instances of Euclidean k-means. (NeurIPS 2017 · similarity 0.88)
- Near-Optimal Private and Scalable $k$-Clustering (NeurIPS 2022 · similarity 0.87)
- Fully-Scalable Massively Parallel Algorithm for k-center with Outliers (AAAI 2025 · similarity 0.87)
- Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling (NeurIPS 2026 · similarity 0.85)
- Efficient Constrained K-center Clustering with Background Knowledge (AAAI 2024 · similarity 0.84)
- Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems (ICLR 2025 · 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.