Probability Measures with Big Kernels
نویسندگان
چکیده
It is shown that in an infinite-dimensional dually separated second category topological vector space X there does not exist a probability measure μ for which the kernel coincides with X. Moreover, we show that in “good” cases the kernel has the full measure if and only if it is finitedimensional. Also, the problem posed by S. Chevet [5, p. 69] is solved by proving that the annihilator of the kernel of a measure μ coincides with the annihilator of μ if and only if the topology of μ-convergence in the dual space is essentially dually separated. 2000 Mathematics Subject Classification: Primary: 60B11. Secondary: 28C20.
منابع مشابه
Injective Hilbert Space Embeddings of Probability Measures
A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing and independence testing. This embedding represents any probability measure as a mean element in a reproducing kernel Hilbert space (RKHS). The embedding function has been proven to be injective when the reproducing kernel is universal. In this...
متن کاملHilbertian Metrics and Positive Definite Kernels on Probability Measures
We investigate the problem of defining Hilbertian metrics resp. positive definite kernels on probability measures, continuing the work in [5]. This type of kernels has shown very good results in text classification and has a wide range of possible applications. In this paper we extend the two-parameter family of Hilbertian metrics of Topsøe such that it now includes all commonly used Hilbertian...
متن کاملUniversality, Characteristic Kernels and RKHS Embedding of Measures
Over the last few years, two different notions of positive definite (pd) kernels—universal and characteristic—have been developing in parallel in machine learning: universal kernels are proposed in the context of achieving the Bayes risk by kernel-based classification/regression algorithms while characteristic kernels are introduced in the context of distinguishing probability measures by embed...
متن کاملSemantic Classification with Distributional Kernels
Distributional measures of lexical similarity and kernel methods for classification are well-known tools in Natural Language Processing. We bring these two methods together by introducing distributional kernels that compare co-occurrence probability distributions. We demonstrate the effectiveness of these kernels by presenting state-of-the-art results on datasets for three semantic classificati...
متن کاملNonextensive Information Theoretic Kernels on Measures
Positive definite kernels on probability measures have been recently applied to classification problems involving text, images, and other types of structured data. Some of these kernels are related to classic information theoretic quantities, such as (Shannon’s) mutual information and the JensenShannon (JS) divergence. Meanwhile, there have been recent advances in nonextensive generalizations o...
متن کامل