Nonasymptotic analysis of robust regression with modified Huber's loss

DOI10.1016/j.jco.2023.101744OpenAlexW4322625819MaRDI QIDQ2693696

Hongzhi Tong

Publication date: 24 March 2023

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2023.101744

zbMATH Keywords

nonparametric regressionconcentration inequalityreproducing kernel Hilbert spaceempirical risk minimizationnonasymptotic analysis

Mathematics Subject Classification ID

Nonparametric robustness (62G35) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• robustbase

Cites Work

• Unnamed Item
• Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Oracle inequalities for support vector machines that are based on random entropy numbers
• Learning under \((1 + \epsilon)\)-moment conditions
• Model selection for regularized least-squares algorithm in learning theory
• A new perspective on robust \(M\)-estimation: finite sample theory and applications to dependence-adjusted multiple testing
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Weak convergence and empirical processes. With applications to statistics
• A statistical learning assessment of Huber regression
• On a regularization of unsupervised domain adaptation in RKHS
• Adaptive Huber regression on Markov-dependent data
• Balancing principle in supervised learning for a general regularization scheme
• 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
• Learning rates of least-square regularized regression
• Local Rademacher complexities
• Learning theory estimates via integral operators and their approximations
• Adaptive Huber Regression
• Support Vector Machines
• Are Loss Functions All the Same?
• New Insights Into Learning With Correntropy-Based Regression
• A robust and efficient variable selection method for linear regression
• An Introduction to Artificial Intelligence Based on Reproducing Kernel Hilbert Spaces
• Robust Variable Selection With Exponential Squared Loss
• How general are general source conditions?
• Robust Estimation of a Location Parameter
• Theory of Reproducing Kernels
• Some applications of concentration inequalities to statistics

This page was built for publication: Nonasymptotic analysis of robust regression with modified Huber's loss