arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01808math.NAcs.NA
收藏

核近似中的尖锐逆定理与饱和:超收敛与饱和

Sharp inverse statements for kernel approximation: Superconvergence and saturation

Ludwig Maximilian University of Munich(慕尼黑路德维希-马克西米利安大学);Munich Center for Machine Learning(慕尼黑机器学习中心)

Tizian Wenzel

AI总结:

本文通过研究核近似中的超收敛区域,建立了目标函数光滑性与逼近速率的对应关系,并扩展了现有结果至更广泛的光滑空间范围。

摘要:

本文利用有限光滑的Sobolev核在有界Lipschitz区域上,建立了核近似中的尖锐逆定理和饱和定理。分析重点在于超收敛区域,此区域的直接定理仅最近才被获得。由此理论得出目标函数的光滑性(以幂空间量化)与核近似可达到的逼近速率之间的一一对应关系。借此,我们扩展了现有结果,超越了逃离原空间区域,并提供了一个统一的特征化,覆盖所有可接受的光滑空间的完整范围。

英文摘要:

This article establishes sharp inverse and saturation statements for kernel-based approximation using finitely smooth Sobolev kernels on bounded Lipschitz regions. The analysis focuses on the superconvergence regime, for which direct statements have only recently been obtained. The resulting theory yields a one-to-one correspondence between the smoothness of a target function - quantified in terms of power spaces - and the achievable approximation rates by kernel-based approximation. In this way, we extend existing results beyond the escaping-the-native-space regime and provide a unified characterization covering the full scale of admissible smoothness spaces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑