中文
相关论文

相关论文: Spectral Norm of Random Kernel Matrices with Appli…

200 篇论文

Kernel methods, particularly kernel ridge regression (KRR), are time-proven, powerful nonparametric regression techniques known for their rich capacity, analytical simplicity, and computational tractability. The analysis of their predictive…

统计理论 · 数学 2025-09-23 Xin Bing , Xin He , Chao Wang

Kernel ridge regression (KRR) is a popular class of machine learning models that has become an important tool for understanding deep learning. Much of the focus thus far has been on studying the proportional asymptotic regime, $n \asymp d$,…

机器学习 · 统计学 2025-10-07 Parthe Pandit , Zhichao Wang , Yizhe Zhu

Kernel ridge regression (KRR) is a well-known and popular nonparametric regression approach with many desirable properties, including minimax rate-optimality in estimating functions that belong to common reproducing kernel Hilbert spaces…

机器学习 · 统计学 2019-10-15 Arash A. Amini

We provide uniform confidence bands for kernel ridge regression (KRR), a widely used nonparametric regression estimator for nonstandard data such as preferences, sequences, and graphs. Despite the prevalence of these data--e.g., student…

统计理论 · 数学 2025-08-19 Rahul Singh , Suhas Vijaykumar

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 explicit feature…

机器学习 · 统计学 2019-02-26 Philip Milton , Emanuele Giorgi , Samir Bhatt

Regularized kernel methods such as, e.g., support vector machines and least-squares support vector regression constitute an important class of standard learning algorithms in machine learning. Theoretical investigations concerning…

机器学习 · 统计学 2012-03-21 Robert Hable

We propose a new method for input variable selection in nonlinear regression. The method is embedded into a kernel regression machine that can model general nonlinear functions, not being a priori limited to additive models. This is the…

机器学习 · 计算机科学 2018-09-05 Magda Gregorová , Jason Ramapuram , Alexandros Kalousis , Stéphane Marchand-Maillet

Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier features are still not…

机器学习 · 计算机科学 2018-05-22 Haim Avron , Michael Kapralov , Cameron Musco , Christopher Musco , Ameya Velingker , Amir Zandieh

We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function $k(\cdot,\cdot)$. Our approach uses decoupling results for U-statistics and the non-commutative…

机器学习 · 统计学 2025-11-07 Chiraag Kaushik , Justin Romberg , Vidya Muthukumar

Kernel methods are successful approaches for different machine learning problems. This success is mainly rooted in using feature maps and kernel matrices. Some methods rely on the eigenvalues/eigenvectors of the kernel matrix, while for…

机器学习 · 计算机科学 2012-02-20 Nima Reyhani , Hideitsu Hino , Ricardo Vigario

We place ourselves in the setting of high-dimensional statistical inference where the number of variables $p$ in a dataset of interest is of the same order of magnitude as the number of observations $n$. We consider the spectrum of certain…

统计理论 · 数学 2010-01-05 Noureddine El Karoui

Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…

机器学习 · 计算机科学 2025-09-11 Chunyang Liao , Deanna Needell , Hayden Schaeffer , Alexander Xue

Random feature mapping (RFM) is a popular method for speeding up kernel methods at the cost of losing a little accuracy. We study kernel ridge regression with random feature mapping (RFM-KRR) and establish novel out-of-sample error upper…

机器学习 · 统计学 2019-09-26 Shusen Wang

Understanding the spectral properties of kernels offers a principled perspective on generalization and representation quality. While deep models achieve state-of-the-art accuracy in molecular property prediction, kernel methods remain…

机器学习 · 计算机科学 2025-10-17 Asma Jamali , Tin Sum Cheng , Rodrigo A. Vargas-Hernández

We consider supervised learning problems within the positive-definite kernel framework, such as kernel ridge regression, kernel logistic regression or the support vector machine. With kernels leading to infinite-dimensional feature spaces,…

机器学习 · 计算机科学 2013-05-23 Francis Bach

The kernel matrix used in kernel methods encodes all the information required for solving complex nonlinear problems defined on data representations in the input space using simple, but implicitly defined, solutions. Spectral analysis on…

机器学习 · 计算机科学 2020-10-26 Alexandros Iosifidis

A common challenge in nonparametric inference is its high computational complexity when data volume is large. In this paper, we develop computationally efficient nonparametric testing by employing a random projection strategy. In the…

统计理论 · 数学 2018-02-20 Meimei Liu , Zuofeng Shang , Guang Cheng

We obtain upper bounds for the estimation error of Kernel Ridge Regression (KRR) for all non-negative regularization parameters, offering a geometric perspective on various phenomena in KRR. As applications: 1. We address the multiple…

统计理论 · 数学 2024-10-10 Georgios Gavrilopoulos , Guillaume Lecué , Zong Shang

Kernel matrices, as well as weighted graphs represented by them, are ubiquitous objects in machine learning, statistics and other related fields. The main drawback of using kernel methods (learning and inference using kernel matrices) is…

机器学习 · 计算机科学 2022-12-02 Ainesh Bakshi , Piotr Indyk , Praneeth Kacham , Sandeep Silwal , Samson Zhou

We investigate random matrices whose entries are obtained by applying a nonlinear kernel function to pairwise inner products between $n$ independent data vectors, drawn uniformly from the unit sphere in $\mathbb{R}^d$. This study is…

概率论 · 数学 2023-05-09 Yue M. Lu , Horng-Tzer Yau
‹ 上一页 1 2 3 10 下一页 ›