A dependence maximization view of clustering

Le Song, Alex Smola, Arthur Gretton, Karsten M. Borgwardt
2007 Proceedings of the 24th international conference on Machine learning - ICML '07  
We propose a family of clustering algorithms based on the maximization of dependence between the input variables and their cluster labels, as expressed by the Hilbert-Schmidt Independence Criterion (HSIC). Under this framework, we unify the geometric, spectral, and statistical dependence views of clustering, and subsume many existing algorithms as special cases (e.g. k-means and spectral clustering). Distinctive to our framework is that kernels can also be applied on the labels, which can endow
more » ... them with particular structures. We also obtain a perturbation bound on the change in k-means clustering.
doi:10.1145/1273496.1273599 dblp:conf/icml/SongSGB07 fatcat:ipek6jxxzzb7vcy3ikbj23lqsm