数学
李普希茨连续性
插值(计算机图形学)
趋同(经济学)
核(代数)
理论(学习稳定性)
应用数学
收敛速度
Lipschitz域
数学分析
纯数学
计算机科学
人工智能
计算机网络
经济增长
运动(物理)
机器学习
频道(广播)
经济
作者
Tizian Wenzel,Gabriele Santin,Bernard Haasdonk
标识
DOI:10.1093/imanum/drae014
摘要
Abstract Error estimates for kernel interpolation in Reproducing Kernel Hilbert Spaces usually assume quite restrictive properties on the shape of the domain, especially in the case of infinitely smooth kernels like the popular Gaussian kernel. In this paper we prove that it is possible to obtain convergence results (in the number of interpolation points) for kernel interpolation for arbitrary domains $\varOmega \subset{\mathbb{R}} ^{d}$, thus allowing for non-Lipschitz domains including e.g., cusps and irregular boundaries. Especially we show that, when going to a smaller domain $\tilde{\varOmega } \subset \varOmega \subset{\mathbb{R}} ^{d}$, the convergence rate does not deteriorate—i.e., the convergence rates are stable with respect to going to a subset. We obtain this by leveraging an analysis of greedy kernel algorithms. The impact of this result is explained on the examples of kernels of finite as well as infinite smoothness. A comparison to approximation in Sobolev spaces is drawn, where the shape of the domain $\varOmega $ has an impact on the approximation properties. Numerical experiments illustrate and confirm the analysis.
科研通智能强力驱动
Strongly Powered by AbleSci AI