Universality, Characteristic Kernels and RKHS Embedding of Measures

Details Universality, Characteristic Kernels and RKHS Embedding of Measures Universality, Characteristic Kernels and RKHS Embedding of Measures

2010-03-03

arxiv.org/abs/1003.0887v1

Statistics

Machine Learning

30 pages, 1 figure

Scientific paper

A Hilbert space embedding for probability measures has recently been proposed, wherein any probability measure is represented as a mean element in a reproducing kernel Hilbert space (RKHS). Such an embedding has found applications in homogeneity testing, independence testing, dimensionality reduction, etc., with the requirement that the reproducing kernel is characteristic, i.e., the embedding is injective. In this paper, we generalize this embedding to finite signed Borel measures, wherein any finite signed Borel measure is represented as a mean element in an RKHS. We show that the proposed embedding is injective if and only if the kernel is universal. This therefore, provides a novel characterization of universal kernels, which are proposed in the context of achieving the Bayes risk by kernel-based classification/regression algorithms. By exploiting this relation between universality and the embedding of finite signed Borel measures into an RKHS, we establish the relation between universal and characteristic kernels.

Affiliated with

Also associated with

No associations

Rating

Universality, Characteristic Kernels and RKHS Embedding of Measures does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Universality, Characteristic Kernels and RKHS Embedding of Measures, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Universality, Characteristic Kernels and RKHS Embedding of Measures will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-558721