@article{5681,
  title = {Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters},
  journal = {Theoretical Computer Science},
  abstract = {We study clustering algorithms based on neighborhood graphs on a random sample of data points. The question we ask is how such a graph should be constructed in order to obtain optimal clustering results. Which type of neighborhood graph should one choose, mutual k-nearest-neighbor or symmetric k-nearest-neighbor? What is the optimal parameter k? In our setting, clusters are defined as connected components of the t-level set of the underlying probability distribution. Clusters are said to be identified in the neighborhood graph if connected components in the graph correspond to the true underlying clusters. Using techniques from random geometric graph theory, we prove bounds on the probability that clusters are identified successfully, both in a noise-free and in a noisy setting. Those bounds lead to several conclusions. First, k has to be chosen surprisingly high (rather of the order n than of the order logn) to maximize the probability of cluster identification. Secondly, the major difference between the mutual and the symmetric k-nearest-neighbor graph occurs when one attempts to detect the most significant cluster only.},
  volume = {410},
  number = {19},
  pages = {1749-1764},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = apr,
  year = {2009},
  slug = {5681},
  author = {Maier, M. and Hein, M. and von Luxburg, U.},
  month_numeric = {4}
}