C o n v e x   Clustering   w i t h               Convex Clustering with        ExemplarBased Models (M17)
Danial Lashkari, Polina Golland
p - empirical distribution ^

· Convex formulation
­ Guaranteed convergence  to global optimum

q = arg min D( p q ) ^
* qQ

· Exemplarbased models
­ Probabilistic mapping of  data to exemplars

Q - convex hull of

exemplar-centered models

MIT Computer Science and Artificial Intelligence Laboratory