Timezone: »

Spectral Regularization for Support Estimation
Ernesto De Vito · Lorenzo Rosasco · Alessandro Toigo

Mon Dec 06 12:00 AM -- 12:00 AM (PST) @ None #None

In this paper we consider the problem of learning from data the support of a probability distribution when the distribution {\em does not} have a density (with respect to some reference measure). We propose a new class of regularized spectral estimators based on a new notion of reproducing kernel Hilbert space, which we call {\em ``completely regular''}. Completely regular kernels allow to capture the relevant geometric and topological properties of an arbitrary probability space. In particular, they are the key ingredient to prove the universal consistency of the spectral estimators and in this respect they are the analogue of universal kernels for supervised problems. Numerical experiments show that spectral estimators compare favorably to state of the art machine learning algorithms for density support estimation.

Author Information

Ernesto De Vito (Universita' di Genova)
Lorenzo Rosasco (University of Genova- MIT - IIT)
Alessandro Toigo (Politecnico di Milano)

More from the Same Authors