Overcoming the limitations of phase transition by higher order analysis of regularization techniques

DOI10.1214/17-AOS1651zbMath1411.62194arXiv1603.07377OpenAlexW2963791198MaRDI QIDQ1991696

Haolei Weng, Arian Maleki, Le Zheng

Publication date: 30 October 2018

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1603.07377

zbMATH Keywords

phase transitionasymptotic mean square errorcomparison of estimatorssecond-order termoptimal tuningbridge regressionsmall error regime

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Linear regression; mixed models (62J05)

Related Items (5)

Characterizing the SLOPE trade-off: a variational perspective and the Donoho-Tanner limit ⋮ Non-asymptotic analysis and inference for an outlyingness induced winsorized mean ⋮ A power analysis for Model-X knockoffs with \(\ell_p\)-regularized statistics ⋮ Which bridge estimator is the best for variable selection? ⋮ LASSO risk and phase transition under dependence

Cites Work

• Sharp MSE bounds for proximal denoising
• High dimensional robust M-estimation: asymptotic variance via approximate message passing
• Robustness in sparse high-dimensional linear models: relative efficiency and robust approximate message passing
• Statistics for high-dimensional data. Methods, theory and applications.
• Sparsity in penalized empirical risk minimization
• SLOPE-adaptive variable selection via convex optimization
• The restricted isometry property and its implications for compressed sensing
• False discoveries occur early on the Lasso path
• Asymptotics for Lasso-type estimators.
• Simultaneous analysis of Lasso and Dantzig selector
• Asymptotic properties of bridge estimators in sparse high-dimensional regression models
• Sparsity oracle inequalities for the Lasso
• High-dimensional centrally symmetric polytopes with neighborliness proportional to dimension
• On robust regression with high-dimensional predictors
• Randomly Spread CDMA: Asymptotics Via Statistical Physics
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Does $\ell _{p}$ -Minimization Outperform $\ell _{1}$ -Minimization?
• A statistical-mechanics approach to large-system analysis of CDMA multiuser detectors
• Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
• A Statistical View of Some Chemometrics Regression Tools
• The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising
• Living on the edge: phase transitions in convex programs with random data
• The LASSO Risk for Gaussian Matrices
• The Noise-Sensitivity Phase Transition in Compressed Sensing
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• Regularization and Variable Selection Via the Elastic Net
• Sparse nonnegative solution of underdetermined linear equations by linear programming
• Neighborliness of randomly projected simplices in high dimensions
• For most large underdetermined systems of equations, the minimal 𝓁₁‐norm near‐solution approximates the sparsest near‐solution
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Consistent parameter estimation for Lasso and approximate message passing
• Unnamed Item
• Unnamed Item

This page was built for publication: Overcoming the limitations of phase transition by higher order analysis of regularization techniques