Kernel Interpolation of High Dimensional Scattered Data
Abstract
Data sites selected from modeling high-dimensional problems often appear scattered in nonpaternalistic 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.
Department(s)
Mathematics
Document Type
Article
DOI
10.1137/22M1519948
Keywords
high dimension, kernel interpolation, random sampling, stochastic approximation
Publication Date
6-1-2024
Recommended Citation
Sun, Xingping; Lin, Shao-Bo; and Chang, Xiangyu, "Kernel Interpolation of High Dimensional Scattered Data" (2024). Faculty Scholarship. 359.
https://bearworks.missouristate.edu/articles00/359
Journal Title
SIAM Journal on Numerical Analysis
