Nonsmooth DC programming approach to the minimum sumofsquares clustering problems
Abstract
This paper introduces an algorithm for solving the minimum sumofsquares clustering problems using their difference of convex representations. A nonsmooth nonconvex optimization formulation of the clustering problem is used to design the algorithm. Characterizations of critical points, stationary points in the sense of generalized gradients and infstationary points of the clustering problem are given. The proposed algorithm is tested and compared with other clustering algorithms using large real world data sets.
 Publication:

Pattern Recognition
 Pub Date:
 May 2016
 DOI:
 10.1016/j.patcog.2015.11.011
 Bibcode:
 2016PatRe..53...12B
 Keywords:

 Cluster analysis;
 Nonsmooth optimization;
 Nonconvex optimization;
 Incremental clustering algorithms