Abstract
A new class of objective functions and an associated fast descent algorithm that generalizes the K-means algorithm is presented. The algorithm represents clusters as unions of Voronoi cells and an explicit, but efficient, combinatorial search phase enables the algorithm to escape many local minima with guaranteed descent. The objective function has explicit penalties for gaps between clusters. Numerical experiments are provided.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
