Why is Fuzzy CMeans compute time varying widely for m?

14 Views Asked by At

I am running a cmeans analysis on a series of 20k document embeddings, with the number of clusters set to 400.

For m (fuzziness parameter) from 2-4, the algorithm completes in hours, however for m <1.5 it is taking days?

I am struggling to understand why this is the case? in my understanding of thigs, m should contribute little to compute time

0

There are 0 best solutions below