LASSO Reloaded: A Variational Analysis Perspective with Applications to Compressed Sensing

DOI10.1137/22M1498991zbMath1530.49025arXiv2205.06872OpenAlexW4389452121MaRDI QIDQ6148354

Aaron Berk, Simone Brugiapaglia, Tim Hoheisel

Publication date: 11 January 2024

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2205.06872

zbMATH Keywords

coderivativevariational analysismetric regularityLASSOcompressed sensinggraphical derivative

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Convex programming (90C25) Sensitivity, stability, well-posedness (49K40) Set-valued and variational analysis (49J53) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Sampling theory in information and communication theory (94A20)

Related Items (1)

Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A mathematical introduction to compressive sensing
• On the solution uniqueness characterization in the L1 norm and polyhedral gauge recovery
• The Lasso problem and uniqueness
• Globalized inexact proximal Newton-type methods for nonconvex composite functions
• An introduction to compressed sensing
• The sparsity of LASSO-type minimizers
• Necessary and sufficient conditions of solution uniqueness in 1-norm minimization
• Stable recovery of analysis based approaches
• Simultaneous analysis of Lasso and Dantzig selector
• The degrees of freedom of partly smooth regularizers
• Correcting for unknown errors in sparse high-dimensional function approximation
• Quadratic growth conditions and uniqueness of optimal solution to Lasso
• On the sparsity of Lasso minimizers in sparse data recovery
• Low Complexity Regularization of Linear Inverse Problems
• Proximal Newton-Type Methods for Minimizing Composite Functions
• On Sparse Representations in Arbitrary Redundant Bases
• Decoding by Linear Programming
• The Bayesian Lasso
• Linear Inversion of Band-Limited Reflection Seismograms
• On the Identification of Active Constraints
• Atomic Decomposition by Basis Pursuit
• Variational Analysis
• Variational Analysis and Applications
• First-Order Methods in Optimization
• High-Dimensional Statistics
• High-Dimensional Probability
• Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
• Active Sets, Nonsmoothness, and Sensitivity
• Sparse Approximate Solutions to Linear Systems
• A Semismooth Newton Method with Multidimensional Filter Globalization for $l_1$-Optimization
• Compressive Imaging: Structure, Sampling, Learning
• <scp>Sub‐Gaussian</scp> Matrices on Sets: Optimal Tail Dependence and Applications
• On the Best Choice of Lasso Program Given Data Parameters
• Sparse Solutions of Underdetermined Linear Systems and Their Applications
• Sensitivity of ℓ1 minimization to parameter choice
• The LASSO Risk for Gaussian Matrices
• Implicit Functions and Solution Mappings
• Stable signal recovery from incomplete and inaccurate measurements
• Convex Analysis
• Convex analysis and monotone operator theory in Hilbert spaces
• Compressed sensing

This page was built for publication: LASSO Reloaded: A Variational Analysis Perspective with Applications to Compressed Sensing