There is a well-known modification of the initializing step of K-means, named K-means++. It chooses cluster centers with probability proportional to its squared distance from the point's closest existing cluster center.

If the data are coming from a mixture distribution of normals, what is the distribution of the cluster centers after the initializing step?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.