News for hackers. Stuff that matters.

A comment on Introduction to K-Means Clustering. Parent comment

Re:Introduction to K-Means Clustering by amilios on Monday March 14, 2022 @01:40PM (#30675439)
The way k-means is constructed is not based on distances.

K-means minimizes within-cluster variance. If you look at the definition of variance, it is identical to the sum of squared Euclidean distances from the centroid

[ Parent | on HN ]
Re:Introduction to K-Means Clustering by nerdponx on Monday March 14, 2022 @01:55PM (#30675645)
Do you lose convergence guarantees if you minimize "sum of squared distances from the centroid" using your other-than-Euclidean distance metric?
[ Parent | on HN ]