Kernel Interpolation of High Dimensional Scattered Data
From MaRDI portal
Publication:6348308
DOI10.1137/22M1519948arXiv2009.01514MaRDI QIDQ6348308FDOQ6348308
Authors: Shaobo Lin, Xiangyu Chang, Xingping Sun 
Publication date: 3 September 2020
Abstract: Data sites selected from modeling high-dimensional problems often appear scattered in non-paternalistic ways. Except for sporadic clustering at some spots, they become relatively far apart as the dimension of the ambient space grows. These features defy any theoretical treatment that requires local or global quasi-uniformity of distribution of data sites. Incorporating a recently-developed application of integral operator theory in machine learning, we propose and study in the current article a new framework to analyze kernel interpolation of high dimensional data, which features bounding stochastic approximation error by the spectrum of the underlying kernel matrix. Both theoretical analysis and numerical simulations show that spectra of kernel matrices are reliable and stable barometers for gauging the performance of kernel-interpolation methods for high dimensional data.
Recommendations
- Multilevel sparse kernel-based interpolation
- Interpolation of sparse high-dimensional data
- Kernel approximation: from regression to interpolation
- Scattered data interpolation on embedded submanifolds with restricted positive definite kernels: Sobolev error estimates
- Scattered data approximation by positive definite kernel functions
Learning and adaptive systems in artificial intelligence (68T05) Sampling theory in information and communication theory (94A20) Approximation by operators (in particular, by integral operators) (41A35)
This page was built for publication: Kernel Interpolation of High Dimensional Scattered Data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6348308)
