中文
相关论文

相关论文: Stability of convergence rates: Kernel interpolati…

200 篇论文

We analyse the convergence of sampling algorithms for functions in reproducing kernel Hilbert spaces (RKHS). To this end, we discuss approximation properties of kernel regression under minimalistic assumptions on both the kernel and the…

机器学习 · 统计学 2025-04-21 Armin Iske

Regularized empirical risk minimization using kernels and their corresponding reproducing kernel Hilbert spaces (RKHSs) plays an important role in machine learning. However, the actually used kernel often depends on one or on a few…

机器学习 · 统计学 2017-09-25 Andreas Christmann , Daohong Xiang , Ding-Xuan Zhou

We show that minimum-norm interpolation in the Reproducing Kernel Hilbert Space corresponding to the Laplace kernel is not consistent if input dimension is constant. The lower bound holds for any choice of kernel bandwidth, even if selected…

机器学习 · 统计学 2018-12-31 Alexander Rakhlin , Xiyu Zhai

Classical convergence analysis for kernel interpolation typically assumes that the target function $f$ lies in the reproducing kernel Hilbert space $\mathcal{H}_k\!\left(\Omega\right)$ induced by a kernel on a domain…

数值分析 · 数学 2025-12-09 Tobias Ehring , Max-Paul Vogel , Bernard Haasdonk

We study the consistency of minimum-norm interpolation in reproducing kernel Hilbert spaces corresponding to bounded kernels. Our main result give lower bounds for the generalization error of the kernel interpolation measured in a…

机器学习 · 统计学 2025-09-30 Yunfei Yang

Kernel interpolation is a fundamental technique for approximating functions from scattered data, with a well-understood convergence theory when interpolating elements of a reproducing kernel Hilbert space. Beyond this classical setting,…

数值分析 · 数学 2025-05-19 Toni Karvonen , Gabriele Santin , Tizian Wenzel

Kernel interpolation is a versatile tool for the approximation of functions from data, and it can be proven to have some optimality properties when used with kernels related to certain Sobolev spaces. In the context of interpolation, the…

数值分析 · 数学 2025-01-09 Gabriele Santin , Tizian Wenzel , Bernard Haasdonk

Kernel-based quadrature rules are becoming important in machine learning and statistics, as they achieve super-$\sqrt{n}$ convergence rates in numerical integration, and thus provide alternatives to Monte Carlo integration in challenging…

机器学习 · 统计学 2016-10-31 Motonobu Kanagawa , Bharath K. Sriperumbudur , Kenji Fukumizu

It is well-known that univariate cubic spline interpolation, if carried out on point sets with fill distance $h$, converges only like ${\cal O}(h^2)$ in $L_2[a,b]$ for functions in $W_2^2[a,b]$ if no additional assumptions are made. But…

数值分析 · 数学 2016-07-15 Robert Schaback

Kernel interpolation in tensor product reproducing kernel Hilbert spaces allows for the use of sparse grids to mitigate the curse of the dimension. Typically, besides the generic constant, only a dimension dependent power of a logarithm…

数值分析 · 数学 2025-12-16 M. Griebel , H. Harbrecht

This short technical report presents some learning theory results on vector-valued reproducing kernel Hilbert space (RKHS) regression, where the input space is allowed to be non-compact and the output space is a (possibly…

机器学习 · 统计学 2022-02-17 Junhyunng Park , Krikamol Muandet

We develop novel learning rates for conditional mean embeddings by applying the theory of interpolation for reproducing kernel Hilbert spaces (RKHS). We derive explicit, adaptive convergence rates for the sample estimator under the…

机器学习 · 统计学 2026-04-09 Prem Talwai , Ali Shameli , David Simchi-Levi

Current methods for stochastic hyperparameter learning in Gaussian Processes (GPs) rely on approximations, such as computing biased stochastic gradients or using inducing points in stochastic variational inference. However, when using such…

机器学习 · 计算机科学 2025-08-29 Neta Shoham , Haim Avron

We prove statistical rates of convergence for kernel-based least squares regression from i.i.d. data using a conjugate gradient algorithm, where regularization against overfitting is obtained by early stopping. This method is related to…

统计理论 · 数学 2016-07-11 Gilles Blanchard , Nicole Krämer

Radial basis functions (RBFs) are prominent examples for reproducing kernels with associated reproducing kernel Hilbert spaces (RKHSs). The convergence theory for the kernel-based interpolation in that space is well understood and optimal…

经典分析与常微分方程 · 数学 2023-09-15 Thomas Hangelbroek , Christian Rieger

This article is devoted to developing a theory for effective kernel interpolation and approximation in a general setting. For a wide class of compact, connected $C^\infty$ Riemannian manifolds, including the important cases of spheres and…

经典分析与常微分方程 · 数学 2015-03-17 T. Hangelbroek , F. J. Narcowich , J. D. Ward

Kernel mean embeddings, a widely used technique in machine learning, map probability distributions to elements of a reproducing kernel Hilbert space (RKHS). For supervised learning problems, where input-output pairs are observed, the…

机器学习 · 统计学 2024-10-24 Ambrus Tamás , Balázs Csanád Csáji

Greedy methods have recently been successfully applied to generalized kernel interpolation, or the recovery of a function from data stemming from the evaluation of linear functionals, including the approximation of solutions of linear PDEs…

数值分析 · 数学 2026-01-29 Bernard Haasdonk , Gabriele Santin , Tizian Wenzel , Daniel Winkle

This paper studies convergence of empirical risks in reproducing kernel Hilbert spaces (RKHS). A conventional assumption in the existing research is that empirical training data do not contain any noise but this may not be satisfied in some…

最优化与控制 · 数学 2020-05-19 Shaoyan Guo , Huifu Xu , Liwei Zhang

We study the concentration of random kernel matrices around their mean. We derive nonasymptotic exponential concentration inequalities for Lipschitz kernels assuming that the data points are independent draws from a class of multivariate…

统计理论 · 数学 2020-01-28 Arash A. Amini , Zahra S. Razaee
‹ 上一页 1 2 3 10 下一页 ›