The degrees of freedom of partly smooth regularizers

DOI10.1007/s10463-016-0563-zzbMath1382.62027arXiv1404.5557MaRDI QIDQ2409395

Jalal Fadili, Gabriel Peyré, Charles Dossal, Charles-Alban Deledalle, Samuel Vaiter

Publication date: 11 October 2017

Published in: Annals of the Institute of Statistical Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1404.5557

zbMATH Keywords

manifold; total variation; model selection; sparsity; group Lasso; degrees of freedom; semi-algebraic sets; O-minimal structures; partial smothness

Mathematics Subject Classification ID

62G08: Nonparametric regression and quantile regression

62H12: Estimation in multivariate analysis

62J07: Ridge regression; shrinkage estimators (Lasso)

62J12: Generalized linear models (logistic models)

90C25: Convex programming

49J52: Nonsmooth analysis

Related Items

CLEAR: Covariant LEAst-Square Refitting with Applications to Image Restoration, Local linear convergence analysis of Primal–Dual splitting methods, Risk estimators for choosing regularization parameters in ill-posed problems -- properties and limitations, Local convergence properties of Douglas-Rachford and alternating direction method of multipliers, The degrees of freedom of partly smooth regularizers, Low Complexity Regularization of Linear Inverse Problems

Uses Software

• PDCO
• PhaseLift

Cites Work

• Nonlinear total variation based noise removal algorithms
• Degrees of freedom in lasso problems
• Statistics for high-dimensional data. Methods, theory and applications.
• Consistent group selection in high-dimensional linear regression
• Near-ideal model selection by \(\ell _{1}\) minimization
• On the degrees of freedom in shrinkage estimation
• Estimation of the mean of a multivariate normal distribution
• Improving upon standard estimators in discrete exponential families with applications to Poisson and negative binomial cases
• A natural identity for exponential families with applications in multiparameter estimation
• The mathematics of eigenvalue optimization
• On the degrees of freedom in shape-restricted regression.
• Geometric categories and o-minimal structures
• Honest variable selection in linear and logistic regression models via \(\ell _{1}\) and \(\ell _{1}+\ell _{2}\) penalization
• Self-concordant analysis for logistic regression
• Local behavior of sparse analysis regularization: applications to risk estimation
• Simultaneous analysis of Lasso and Dantzig selector
• The degrees of freedom of partly smooth regularizers
• High-dimensional generalized linear models and the lasso
• On the ``degrees of freedom of the lasso
• High-dimensional graphs and variable selection with the Lasso
• Newton methods for nonsmooth convex minimization: connections among \(\mathcal U\)-Lagrangian, Riemannian Newton and SQP methods
• Exact matrix completion via convex optimization
• Twice Differentiable Spectral Functions
• PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
• Orthogonal Invariance and Identifiability
• Robust principal component analysis?
• Identifiable Surfaces in Constrained Optimization
• Generic Optimality Conditions for Semialgebraic Convex Programs
• Activity Identification and Local Linear Convergence of Douglas–Rachford/ADMM under Partial Smoothness
• Geometrical interpretation of the predictor-corrector type algorithms in structured optimization problems
• Model selection and estimation in the Gaussian graphical model
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• The Group Lasso for Logistic Regression
• GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear Systems
• How Biased is the Apparent Error Rate of a Prediction Rule?
• Atomic Decomposition by Basis Pursuit
• A new approach to variable selection in least squares problems
• Model Consistency of Partly Smooth Regularizers
• Generalized SURE for Exponential Families: Applications to Regularization
• Unbiased Risk Estimates for Singular Value Thresholding and Spectral Estimators
• Model selection with low complexity priors
• Sparsity and Smoothness Via the Fused Lasso
• The 𝒰-Lagrangian of a convex function
• Active Sets, Nonsmoothness, and Sensitivity
• Equivalent Subgradient Versions of Hamiltonian and Euler–Lagrange Equations in Variational Analysis
• The degrees of freedom of the Lasso for general design matrix
• Stein Unbiased GrAdient estimator of the Risk (SUGAR) for Multiple Parameter Selection
• Generic nondegeneracy in convex optimization
• Uncertainty Principles and Vector Quantization
• Partial Smoothness, Tilt Stability, and Generalized Hessians
• An Extrinsic Look at the Riemannian Hessian
• Model Selection and Estimation in Regression with Grouped Variables
• For most large underdetermined systems of linear equations the minimal 𝓁₁‐norm solution is also the sparsest solution
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item