Research map / Learning theory and algorithms / Clustering
The Complexity of k-Means Clustering when Little is Known
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 |
|---|---|---|---|
| Parameterize bounded-domain MCME by incidence treewidth of the mask (no k in parameter) instead of k plus incidence treewidth | Bounded-domain MCME · theoretical (FPT analysis) | fixed-parameter tractability | Helped |
| Use primal graph treewidth of the mask as the parameter for real-valued MCME | Real-valued MCME · theoretical (FPT analysis) | fixed-parameter tractability | Helped |
| Use local feedback edge number of the incidence graph as the parameter for real-valued MCME | Real-valued MCME · theoretical (FPT analysis) | fixed-parameter tractability | Helped |
| Trivial solution when k is large: if k >= (tw(GI)+1)|D|^(tw(GI)+1), a zero-cost matrix always exists | Bounded-domain MCME · theoretical (Lemma 2) | solution existence | Helped |
Closest papers by meaning
- Simple and Scalable Sparse k-means Clustering via Feature Ranking (NeurIPS 2020 · similarity 0.91)
- The Parameterized Complexity of Clustering Incomplete Data (AAAI 2021 · similarity 0.91)
- Improved Learning-augmented Algorithms for k-means and k-medians Clustering (ICLR 2023 · similarity 0.91)
- A Sampling-Based Approach for Efficient Clustering in Large Datasets (CVPR 2022 · similarity 0.89)
- Simple, Scalable and Effective Clustering via One-Dimensional Projections (NeurIPS 2023 · similarity 0.89)
- Explainable k-Means and k-Medians Clustering (ICML 2020 · similarity 0.89)
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.