Approximation of high-dimensional kernel matrices by multilevel circulant matrices
The authors approximate the kernel matrix of a high-dimensional kernel by a nice matrix with a significantly lower computational cost when calculating the inverse of its regularized matrix. Multilevel circulant matrices are a good choice since they are convenient to calculate their inverses. The built-in periodicity of these matrices allows the use of the multi-dimensional fast Fourier transform in calculating their inverses at the cost of \(O(n\log n)\) multiplications. The fast discrete algorithms for sparse Fourier expansions of high-dimensional data can be applied to obtain an even faster algorithm. Convergence for the approximation of kernel matrices by multilevel circulant matrices is analyzed under the assumption that the kernel matrices have an exponential or polynomial decay when their elements are both away from the diagonal and from the corners of the matrices at each level. Compactly supported kernels are also considered. The development presented in this paper for high-dimensional kernels is not a trivial extension of the one-dimensional results.
- Approximation of kernel matrices by circulant matrices and its application in kernel selection methods
- Learning in high-dimensional feature spaces using ANOVA-based fast matrix-vector multiplication
- Far-field compression for fast kernel summation methods in high dimensions
- Multidimensional butterfly factorization
- Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity
- A practical guide to splines
- A unifying approach to some old and new theorems on distribution and clustering
- Approximation of kernel matrices by circulant matrices and its application in kernel selection methods
- Approximation theory in tensor product spaces
- Fast discrete algorithms for sparse Fourier expansions of high dimensional functions
- scientific article; zbMATH DE number 3650737 (Why is no real title available?)
- scientific article; zbMATH DE number 89017 (Why is no real title available?)
- scientific article; zbMATH DE number 3601500 (Why is no real title available?)
- scientific article; zbMATH DE number 1249106 (Why is no real title available?)
- scientific article; zbMATH DE number 1391397 (Why is no real title available?)
- Kernel techniques: From machine learning to meshless methods
- Learning the kernel function via regularization
- Lectures on Fourier Integrals. (AM-42)
- On a kernel-based method for pattern recognition, regression, approximation, and operator inversion
- Propriétés des matrices ``bien localisées près de leur diagonale et quelques applications. (Properties of matrices ``well localized near the diagonal and some applications)
- Refinable kernels
- Regularization networks and support vector machines
- Reproducing kernel Banach spaces for machine learning
- The optimal recovery of smooth functions
- Theory of Reproducing Kernels
- Universal kernels
- On the minimal polynomials and the inverses of multilevel scaled factor circulant matrices
- Learning in high-dimensional feature spaces using ANOVA-based fast matrix-vector multiplication
- Approximation of kernel matrices by circulant matrices and its application in kernel selection methods
- Far-field compression for fast kernel summation methods in high dimensions
- Reproducing kernel Banach spaces with the \(\ell^{1}\) norm. II: Error analysis for regularized least square regression
- Fast Deterministic Approximation of Symmetric Indefinite Kernel Matrices with High Dimensional Datasets
- Generalized Mercer kernels and reproducing kernel Banach spaces
- High-dimensional approximation with kernel-based multilevel methods on sparse grids
- Fast kernel summation in high dimensions via slicing and Fourier transforms
- A matrix nearness problem constrained on the kernel space of multilevel (R, S_)-commutative matrices
- Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity
This page was built for publication: Approximation of high-dimensional kernel matrices by multilevel circulant matrices
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q990819)
