A sharp nonasymptotic bound and phase diagram of \(L_{1/2}\) regularization

DOI10.1007/s10114-014-0466-yzbMath1305.62258OpenAlexW1995528644MaRDI QIDQ477827

Zong Ben Xu, Xiang Yu Chang, Yao Wang, Yong Liang, Hai Zhang

Publication date: 10 December 2014

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

Full work available at URL: https://doi.org/10.1007/s10114-014-0466-y

zbMATH Keywords

phase diagramcompressive sensing\(L_{1/2}\) regularization

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Computational learning theory (68Q32)

Related Items

Bayesian joint inference for multivariate quantile regression model with \(L_{1/2}\) penalty

Uses Software

• UCI-ml
• PDCO

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Adaptive Lasso and Its Oracle Properties
• The essential ability of sparse reconstruction of different compressive sensing strategies
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• Some sharp performance bounds for least squares regression with \(L_1\) regularization
• The sparsity and bias of the LASSO selection in high-dimensional linear regression
• Estimating the dimension of a model
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• Nonconcave penalized likelihood with a diverging number of parameters.
• Least angle regression. (With discussion)
• Simultaneous analysis of Lasso and Dantzig selector
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• High-dimensional centrally symmetric polytopes with neighborliness proportional to dimension
• Piecewise linear regularized solution paths
• Atomic Decomposition by Basis Pursuit
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Decoding by Linear Programming
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
• Uncertainty principles and ideal atomic decomposition
• Regularization and Variable Selection Via the Elastic Net
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ ¹ minimization
• Compressed sensing