We formulate weighted graph clustering as a prediction problem1 : given a subset of edge weights we analyze the ability of graph clustering to predict the remaining edge weights. ...
Nearest neighbor classification assumes locally constant class conditional probabilities. This assumption becomes invalid in high dimensions with finite samples due to the curse o...
An important aspect of clustering algorithms is whether the partitions constructed on finite samples converge to a useful clustering of the whole data space as the sample size inc...
Ulrike von Luxburg, Olivier Bousquet, Mikhail Belk...
Pointwise consistent, feasible procedures for estimating contemporaneous linear causal structure from time series data have been developed using multiple conditional independence ...
The eigenvalues of the kernel matrix play an important role in a number of kernel methods, in particular, in kernel principal component analysis. It is well known that the eigenva...