Good (K-means) clusterings are unique (up to small perturbations) (Q2274925): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Removed claim: reviewed by (P1447): Item:Q278551 |
||
| Property / reviewed by | |||
| Property / reviewed by: Denis Nikolaevich Sidorov / rank | |||
Revision as of 13:55, 12 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Good (K-means) clusterings are unique (up to small perturbations) |
scientific article |
Statements
Good (K-means) clusterings are unique (up to small perturbations) (English)
0 references
1 October 2019
0 references
Under the assumption that clustering with small K-means distortion is close to the optimal clustering, this paper reports that the distance \(d(X, X_{opt})\), for any K-clustering \(X\) whose cost is sufficiently low, can be bounded above by a value that depends only on known quantities.
0 references
K-means clustering
0 references
spectral clustering
0 references
cluster validation
0 references
model free
0 references
clusterability
0 references
