Convex Relaxations of Bregman Divergence Clustering
Hao Cheng, Xinhua Zhang, Dale Schuurmans
Although many convex relaxations of clustering have been proposed in the past decade, current formulations remain restricted to spherical Gaussian or discriminative models and are susceptible to imbalanced clusters. To address these shortcomings, we propose a new class of convex relaxations that can be flexibly applied to more general forms of Bregman divergence clustering. By basing these new formulations on normalized equivalence relations we retain additional control on relaxation quality, which allows improvement in clustering quality. We furthermore develop optimization methods that improve scalability by exploiting recent implicit matrix norm methods. In practice, we find that the new formulations are able to efficiently produce tighter clusterings that improve the accuracy of state of the art methods.
PDF Link: /papers/13/p162-cheng.pdf
AUTHOR = "Hao Cheng
and Xinhua Zhang and Dale Schuurmans",
TITLE = "Convex Relaxations of Bregman Divergence Clustering",
BOOKTITLE = "Proceedings of the Twenty-Ninth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-13)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2013",
PAGES = "162--171"