Eigencluster is an experimental search-and-cluster engine based on a spectral algorithm from On clusterings: good, bad, and spectral [Journal of the ACM (JACM) 51(3), 497--515, 2004]. The implementation used here is described and studied in A Divide and Merge Methodology for Clustering [To appear in Transactions on Database Systems].

If you have any questions, please contact Ravi Kannan, Santosh Vempala, or Grant Wang.


If you are interested in using the algorithm for clustering other data, see http://eigencluster.csail.mit.edu/cluster.html. We would be interested to hear of any uses of the algorithm, so please email us.