Clustering using sum-of-norms regularization; with application to particle filter output computation, Report no. LiTH-ISY-R-2993

We present a novel clustering method, SON clustering, formulated as a convex optimization problem. The method is based on over-parameterization and uses a sum-of-norms regularization to control the trade-o between the model t and the number of clusters. Hence, the number of clusters can be automatically adapted to best describe the data, and need not to be speci ed a priori. We apply SON clustering to cluster the particles in a particle lter, an application where the number of clusters is often unknown and time varying, making SON clustering an attractive alternative.