An elementary analysis of ridge regression with random design

DOI10.5802/crmath.367OpenAlexW4297998635MaRDI QIDQ2080945

Lorenzo Rosasco, Jaouad Mourtada

Publication date: 12 October 2022

Published in: Comptes Rendus. Mathématique. Académie des Sciences, Paris (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.08564

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07) Random matrices (probabilistic aspects) (60B20)

Related Items (1)

High-Dimensional Analysis of Double Descent for Linear Regression with Random Projections

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Performance of empirical risk minimization in linear aggregation
• Nonparametric stochastic approximation with large step-sizes
• The lower tail of random quadratic forms with applications to ordinary least squares
• Random design analysis of ridge regression
• Concentration inequalities and moment bounds for sample covariance operators
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Sums of random Hermitian matrices and an inequality by Rudelson
• Optimal rates for regularization of statistical inverse learning problems
• User-friendly tail bounds for sums of random matrices
• Model selection for regularized least-squares algorithm in learning theory
• Non commutative Khintchine and Paley inequalities
• Random vectors in the isotropic position
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Distribution-free robust linear regression
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Optimal rates for the regularized least-squares algorithm
• Shannon sampling. II: Connections to learning theory
• Local Rademacher complexities
• Learning theory estimates via integral operators and their approximations
• On early stopping in gradient descent learning
• Support Vector Machines
• Strong converse for identification via quantum channels
• 10.1162/1532443041424337
• Benign overfitting in linear regression
• Theory of Reproducing Kernels
• Some applications of concentration inequalities to statistics

This page was built for publication: An elementary analysis of ridge regression with random design