The optimal assignment kernel is not positive definite
نویسنده
چکیده
We prove that the optimal assignment kernel, proposed recently as an attempt to embed labeled graphs and more generally tuples of basic data to a Hilbert space, is in fact not always positive definite.
منابع مشابه
On Valid Optimal Assignment Kernels and Applications to Graph Classification
The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data. A leading design paradigm for this is the convolution kernel, which decomposes structured objects into their parts and sums over all pairs of parts. Assignment kernels, in contrast, are obtained from an optimal bijection between parts, which can provide a more vali...
متن کاملError Analysis of Generalized Nyström Kernel Regression
Nyström method has been successfully used to improve the computational efficiency of kernel ridge regression (KRR). Recently, theoretical analysis of Nyström KRR, including generalization bound and convergence rate, has been established based on reproducing kernel Hilbert space (RKHS) associated with the symmetric positive semi-definite kernel. However, in real world applications, RKHS is not a...
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 کاملNear-Optimal Coresets of Kernel Density Estimates
We construct near-optimal coresets for kernel density estimate for points in Rd when the kernel is positive definite. Specifically we show a polynomial time construction for a coreset of size O( √ d log(1/ε)/ε), and we show a near-matching lower bound of size Ω( √ d/ε). The upper bound is a polynomial in 1/ε improvement when d ∈ [3, 1/ε2) (for all kernels except the Gaussian kernel which had a ...
متن کاملHigher-order accurate, positive semi-definite estimation of large-sample covariance and spectral density matrices
A new class of large-sample covariance and spectral density matrix estimators is proposed based on the notion of flat-top kernels. The new estimators are shown to be higher-order accurate when higher-order accuracy is possible. A discussion on kernel choice is presented as well as a supporting finite-sample simulation. The problem of spectral estimation under a potential lack of finite fourth m...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/0801.4061 شماره
صفحات -
تاریخ انتشار 2008