stat.MLNov 13, 2026

Training-point consistency of kernel ridge regression with varying correlation scales

Authors: Weiyan Mu, Shifeng Xiong, Yuming Shen

Organizations: School of Science, Beijing University of Civil Engineering and Architecture, Beijing, China · SKLMS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China · School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China · School of Information Science and Technology, Guangdong University of Foreign Studies, Guangzhou, China

Abstract

The scale parameter in kernel ridge regression plays a pivotal role in modeling the correlation structure of data. In modern applications, sampling density and the underlying correlation range often change simultaneously, making a fixed-scale assumption highly restrictive. However, establishing asymptotic theories under varying scale parameters is fundamentally challenging. To address this gap, this paper develops a unified theoretical framework for kernel ridge regression under varying scale parameters. We establish that, on uniform tensor grids with product exponential kernels, the consistency of the training-point risk holds if and only if the effective local sample size diverges to infinity. This sharp criterion universally covers all regimes along arbitrary deterministic scale sequences, seamlessly unifying the long-range, fixed-scale, and short-range. Furthermore, we provide an explicit, signal-independent construction of a deterministic regularization penalty that guarantees this consistency. Numerical experiments illustrate the criterion and the corresponding penalty across all the three regimes.

Figures & tables

Explore similar work

CardsList
  1. Large Dimensional Kernel Ridge Regression: Extending to Product Kernels

    May 14, 2026Yang Zhou, Yicheng Li, Yuqian Cheng +1Generalization BoundsKernel Ridge Regression

  2. Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees

    Aug 26, 2026Caixing Wang, Zhibo Chen, Yue WangRandom Feature MethodsKernel Ridge Regression

  3. Kriging via variably scaled kernels

    Mar 16, 2026Gianluca Audone, Francesco Marchetti, Emma Perracchione +1Gaussian ProcessesGaussian Process Regression