A Note On k-Means Probabilistic Poverty
arXiv:1910.00413v21 citations
Originality Synthesis-oriented
AI Analysis
This is an incremental theoretical result for researchers in clustering algorithms, highlighting a limitation in k-means.
The paper demonstrates that k-means with random initialization fails to achieve probabilistic k-richness, as proven through a counterexample.
It is proven, by example, that the version of $k$-means with random initialization does not have the property probabilistic k-richness.