We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the -adapted-dimension, which...
It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, ...
We present a kernel-based algorithm for hierarchical text classification where the documents are allowed to belong to more than one category at a time. The classification model is...
Craig Saunders, John Shawe-Taylor, Juho Rousu, S&a...