Oracle inequality for sparse trace regression models with exponential \(\beta\)-mixing errors

DOI10.1007/s10114-023-2153-3MaRDI QIDQ6063342

Xiangyong Tan, Pei Wen Xiao, Zeinab Rizk, Xiao Hui Liu, Ling Peng

Publication date: 7 November 2023

Published in: Acta Mathematica Sinica. English Series (Search for Journal in Brave)

zbMATH Keywords

oracle inequalitylow-rank matrixtrace regression modelexponential \(\beta\)-mixing errors

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Ridge regression; shrinkage estimators (Lasso) (62J07)

Cites Work

• Unnamed Item
• Unnamed Item
• Nearly unbiased variable selection under minimax concave penalty
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Estimating beta-mixing coefficients via histograms
• Rates of convergence for empirical processes of stationary mixing sequences
• Trace regression model with simultaneously low rank and row(column) sparse parameter
• Lasso guarantees for \(\beta \)-mixing heavy-tailed time series
• Sparse trace norm regularization
• Generalized high-dimensional trace regression via nuclear norm regularization
• Lasso for sparse linear regression with exponentially \(\beta\)-mixing errors
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Square‐Root LASSO for High‐Dimensional Sparse Linear Systems with Weakly Dependent Errors
• High-Dimensional Probability
• Probability Inequalities
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers

This page was built for publication: Oracle inequality for sparse trace regression models with exponential \(\beta\)-mixing errors