paper-with-me

Papers

High-dimensional ridge regression with random features for non-identically distributed data with a variance profile

2025-04-03 · Issa-Mbenard Dabo, Jérémie Bigot

The behavior of the random feature model in the high-dimensional regression framework has become a popular issue of interest in the machine learning literature}. This model is generally considered for feature vectors $x_i = \Sigma^{1/2} x_i'$, where $x_i'$ is a random vector made of independent and identically distributed (iid) entries, and $\Sigma$ is a positive definite matrix representing the covariance of the features. In this paper, we move beyond {\CB this standard assumption by studying the performances of the random features model in the setting of non-iid feature vectors}. Our approach is related to the analysis of the spectrum of large random matrices through random matrix theory (RMT) {\CB and free probability} results. We turn to the analysis of non-iid data by using the notion of variance profile {\CB which} is {\CB well studied in RMT.} Our main contribution is then the study of the limits of the training and {\CB prediction} risks associated to the ridge estimator in the random features model when its dimensions grow. We provide asymptotic equivalents of these risks that capture the behavior of ridge regression with random features in a {\CB high-dimensional} framework. These asymptotic equivalents, {\CB which prove to be sharp in numerical experiments}, are retrieved by adapting, to our setting, established results from operator-valued free probability theory. Moreover, {\CB for various classes of random feature vectors that have not been considered so far in the literature}, our approach allows to show the appearance of the double descent phenomenon when the ridge regularization parameter is small enough.

📄 PDF Abstract BibTeX arXiv:2504.03035

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile

2024-03-29 · Jérémie Bigot, Issa-Mbenard Dabo, Camille Male

High-dimensional linear regression has been thoroughly studied in the context of independent and identically distributed data. We propose to investigate high-dimensional regression models for independent but non-identica…

regression

Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration

2021-01-26 · Song Mei, Theodor Misiakiewicz, Andrea Montanari

Consider the classical supervised learning problem: we are given data $(y_i,{\boldsymbol x}_i)$, $i\le n$, with $y_i$ a response and ${\boldsymbol x}_i\in {\mathcal X}$ a covariates vector, and try to learn a model $f:{\…

regression

Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees

2018-04-26 · ICML 2017 8 · Haim Avron, Michael Kapralov, Cameron Musco, Christopher Musco 외

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 fe…

regression

Error Bounds for Learning with Vector-Valued Random Features

2023-05-26 · NeurIPS 2023 11 · Samuel Lanthaler, Nicholas H. Nelsen

This paper provides a comprehensive error analysis of learning with vector-valued random features (RF). The theory is developed for RF ridge regression in a fully general infinite-dimensional input-output setting, but no…

regression

High-Dimensional Asymptotics of Prediction: Ridge Regression and Classification

2015-07-10 · Edgar Dobriban, Stefan Wager

We provide a unified analysis of the predictive risk of ridge regression and regularized discriminant analysis in a dense random effects model. We work in a high-dimensional asymptotic regime where $p, n \to \infty$ and …

ClassificationGeneral ClassificationregressionVocal Bursts Intensity Prediction