An LP relaxation for K-means is shown to be tight under sufficient conditions for two clusters with recovery guarantees under a stochastic model, plus a scalable cutting-plane algorithm for n up to 4000.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the power of linear programming for K-means clustering
An LP relaxation for K-means is shown to be tight under sufficient conditions for two clusters with recovery guarantees under a stochastic model, plus a scalable cutting-plane algorithm for n up to 4000.