paper-with-me

홈 › Papers

Large Dimensional Kernel Ridge Regression: Extending to Product Kernels

2026-05-14 · Yang Zhou, Yicheng Li, Yuqian Cheng, Qian Lin arxiv

Recent studies have reported $\textit{saturation effects}$ and $\textit{multiple descent behavior}$ in large dimensional kernel ridge regression (KRR). However, these findings are predominantly derived under restrictive settings, such as inner product kernels on sphere or strong eigenfunction assumptions like hypercontractivity. Whether such behaviors hold for other kernels remains an open question. In this paper, we establish a broad, new family of large dimensional kernels and derive the corresponding convergence rates of the generalization error. As a result, we recover key phenomena previously associated with inner product kernels on sphere, including: $i)$ the $\textit{minimax optimality}$ when the source condition $s\le 1$; $ii)$ the $\textit{saturation effect}$ when $s>1$; $iii)$ a $\textit{periodic plateau phenomenon}$ in the convergence rate and a $\textit {multiple-descent behavior}$ with respect to the sample size $n$.

📄 PDF Abstract BibTeX arXiv:2605.14524

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Spatial Analysis Made Easy with Linear Regression and Kernels

2019-02-22 · Philip Milton, Emanuele Giorgi, Samir Bhatt

Kernel methods are an incredibly popular technique for extending linear models to non-linear problems via a mapping to an implicit, high-dimensional feature space. While kernel methods are computationally cheaper than an…

regression

Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data

2019-04-19 · Khalil Elkhalil, Abla Kammoun, Xiangliang Zhang, Mohamed-Slim Alouini 외

This paper carries out a large dimensional analysis of a variation of kernel ridge regression that we call \emph{centered kernel ridge regression} (CKRR), also known in the literature as kernel ridge regression with offs…

regression

Multiple Operator-valued Kernel Learning

2012-12-01 · NeurIPS 2012 12 · Hachem Kadri, Alain Rakotomamonjy, Philippe Preux, Francis R. Bach

Positive definite operator-valued kernels generalize the well-known notion of reproducing kernels, and are naturally adapted to multi-output learning situations. This paper addresses the problem of learning a finite line…

regression

Distributed Generalized Cross-Validation for Divide-and-Conquer Kernel Ridge Regression and its Asymptotic Optimality

2016-12-18 · ICML 2018 7 · Ganggang Xu, Zuofeng Shang, Guang Cheng

Tuning parameter selection is of critical importance for kernel ridge regression. To this date, data driven tuning method for divide-and-conquer kernel ridge regression (d-KRR) has been lacking in the literature, which l…

regression

Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions

2024-01-02 · Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin

Motivated by the studies of neural networks (e.g.,the neural tangent kernel theory), we perform a study on the large-dimensional behavior of kernel ridge regression (KRR) where the sample size $n \asymp d^{\gamma}$ for s…

regression