arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09040math.STstat.TH
收藏

基于核的约束最优平滑逼近的误差界

Error Bounds for a Kernel-Based Constrained Optimal Smoothing Approximation

Laurence Grammont, François Bachoc, Andrés F. López-Lopera

AI总结:

本文为再生核希尔伯特空间中约束最优平滑问题的分段线性逼近建立了误差界,以网格大小、核正则性及到约束集的距离为函数,并允许非等距非稠密节点,通过数值实验验证了理论结果。

摘要:

本文针对在再生核希尔伯特空间(RKHS)中提出的约束最优平滑问题的分段线性逼近的收敛性建立了误差界。该问题可以重新表述为一个贝叶斯估计问题,其中涉及与RKHS核相关的高斯过程。因此,误差界可以被解释为对最大后验(MAP)精度的量化。据我们所知,目前尚未针对此类问题提出过误差界。收敛结果以网格大小、核的正则性以及逼近的核插值到约束集的距离为函数给出。受近期文献中MaxMod算法的启发,该算法顺序分配用于分段线性逼近的节点,我们对非等距节点进行了分析。这些节点甚至允许非稠密,这影响了最优平滑解的定义和我们的误差界量化指标。最后,我们通过涉及有界性和单调性等约束的多个数值实验来说明我们的定理。

英文摘要:

This paper establishes error bounds for the convergence of a piecewise linear approximation of the constrained optimal smoothing problem posed in a reproducing kernel Hilbert space (RKHS). This problem can be reformulated as a Bayesian estimation problem involving a Gaussian process related to the kernel of the RKHS. Consequently, error bounds can be interpreted as a quantification of the maximum a posteriori (MAP) accuracy. To our knowledge, no error bounds have been proposed for this type of problem so far. The convergence results are provided as a function of the grid size, the regularity of the kernel, and the distance from the kernel interpolant of the approximation to the set of constraints. Inspired by the MaxMod algorithm from recent literature, which sequentially allocates knots for the piecewise linear approximation, we conduct our analysis for non-equispaced knots. These knots are even allowed to be non-dense, which impacts the definition of the optimal smoothing solution and our error bound quantifiers. Finally, we illustrate our theorems through several numerical experiments involving constraints such as boundedness and monotonicity.

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。

↑