Conditionally Positive Definite Kernels and Pontryagin Spaces
نویسندگان
چکیده
Conditionally positive definite kernels provide a powerful tool for scattered data approximation. Many nice properties of such methods follow from an underlying reproducing kernel structure. While the connection between positive definite kernels and reproducing kernel Hilbert spaces is well understood, the analog relation between conditionally positive definite kernels and reproducing kernel Pontryagin spaces is less known. We want to provide a theoretical framework which allows to study approximation with conditionally positive definite kernels in associated Pontryagin spaces. §
منابع مشابه
Efficient and Invariant Regularisation with Application to Computer Graphics
This thesis develops the theory and practise of reproducing kernel methods. Many functional inverse problems which arise in, for example, machine learning and computer graphics, have been treated with practical success using methods based on a reproducing kernel Hilbert space perspective. This perspective is often theoretically convenient, in that many functional analysis problems reduce to lin...
متن کاملFeature Space Interpretation of SVMs with non Positive Definite Kernels
The widespread habit of “plugging” arbitrary symmetric functions as kernels in support vector machines (SVMs) often yields good empirical classification results. However, in case of non conditionally positive definite (non-cpd) functions they are hard to interpret due to missing geometrical and theoretical understanding. In this paper we provide a step towards comprehension of SVM classifiers i...
متن کاملConditionally positive definite kernels: theoritical contribution, application to interpolation and approximation
Since Aronszajn (1950), it is well known that a functional Hilbert space, called Reproducing Kernel Hilbert Space (R.K.H.S ), can be associated to any positive definite kernel K. This correspondance is the basis of many useful algorithms. In the more general context of conditionally positive definite kernels the native spaces are the usual theoretical framework. However, the definition of condi...
متن کاملOn the Schoenberg Transformations in Data Analysis: Theory and Illustrations
The class of Schoenberg transformations, embedding Euclidean distances into higher dimensional Euclidean spaces, is presented, and derived from theorems on positive definite and conditionally negative definite matrices. Original results on the arc lengths, angles and curvature of the transformations are proposed, and visualized on artificial data sets by classical multidimensional scaling. A si...
متن کاملConditionally Positive Definite Kernels and Infinitely Divisible Distributions
We give a precise characterization of two important classes of conditionally positive definite (CPD) kernels in terms of integral transforms of infinitely divisible distributions. In particular, we show that for any stationary CPD kernel A(x, y) = f(x − y), f is the log-characteristic function of a uniquely determined infinitely divisible distribution; further, for any additive CPD kernel A(x, ...
متن کامل