LASSO Reloaded: A Variational Analysis Perspective with Applications to Compressed Sensing
From MaRDI portal
Set-valued and variational analysis (49J53) Sensitivity, stability, well-posedness (49K40) Ridge regression; shrinkage estimators (Lasso) (62J07) Convex programming (90C25) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Sampling theory in information and communication theory (94A20)
Abstract: This paper provides a variational analysis of the unconstrained formulation of the LASSO problem, ubiquitous in statistical learning, signal processing, and inverse problems. In particular, we establish smoothness results for the optimal value as well as Lipschitz properties of the optimal solution as functions of the right-hand side (or measurement vector) and the regularization parameter. Moreover, we show how to apply the proposed variational analysis to study the sensitivity of the optimal solution to the tuning parameter in the context of compressed sensing with subgaussian measurements. Our theoretical findings are validated by numerical experiments.
Recommendations
- Square root LASSO: well-posedness, Lipschitz stability, and the tuning trade-off
- Sensitivity of _1 minimization to parameter choice
- Properties and iterative methods for the lasso and its variants
- Templates for convex cone problems with applications to sparse signal recovery
- Consistent parameter estimation for Lasso and approximate message passing
Cites work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A mathematical introduction to compressive sensing
- A semismooth Newton method with multidimensional filter globalization for l₁-optimization
- Active Sets, Nonsmoothness, and Sensitivity
- An introduction to compressed sensing
- Atomic Decomposition by Basis Pursuit
- Characterization of metric regularity of subdifferentials
- Compressed sensing
- Compressive imaging: structure, sampling, learning. With contributions by Vegard Antun
- Convex Analysis
- Convex analysis and monotone operator theory in Hilbert spaces
- Correcting for unknown errors in sparse high-dimensional function approximation
- Decoding by Linear Programming
- First-order methods in optimization
- Globalized inexact proximal Newton-type methods for nonconvex composite functions
- High-dimensional probability. An introduction with applications in data science
- High-dimensional statistics. A non-asymptotic viewpoint
- scientific article; zbMATH DE number 1502618 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 6125590 (Why is no real title available?)
- scientific article; zbMATH DE number 6438182 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Implicit Functions and Solution Mappings
- Linear Inversion of Band-Limited Reflection Seismograms
- Low complexity regularization of linear inverse problems
- Necessary and sufficient conditions of solution uniqueness in 1-norm minimization
- On Sparse Representations in Arbitrary Redundant Bases
- On the Best Choice of Lasso Program Given Data Parameters
- On the Identification of Active Constraints
- On the solution uniqueness characterization in the L1 norm and polyhedral gauge recovery
- On the sparsity of Lasso minimizers in sparse data recovery
- Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
- Proximal Newton-type methods for minimizing composite functions
- Quadratic growth conditions and uniqueness of optimal solution to Lasso
- Scikit-learn: machine learning in Python
- Sensitivity of _1 minimization to parameter choice
- Simultaneous analysis of Lasso and Dantzig selector
- Sparse Approximate Solutions to Linear Systems
- Sparse Solutions of Underdetermined Linear Systems and Their Applications
- Stable recovery of analysis based approaches
- Stable signal recovery from incomplete and inaccurate measurements
- Sub-Gaussian matrices on sets: optimal tail dependence and applications
- The Bayesian Lasso
- The degrees of freedom of partly smooth regularizers
- The Lasso problem and uniqueness
- The LASSO Risk for Gaussian Matrices
- The sparsity of LASSO-type minimizers
- Variational Analysis
- Variational analysis and applications
Cited in
(4)- Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems
- Square root LASSO: well-posedness, Lipschitz stability, and the tuning trade-off
- Geometric characterizations of Lipschitz stability for convex optimization problems
- Towards efficient optimization of sparse regularized separable nonlinear problems: a novel decoupled strategy
This page was built for publication: LASSO Reloaded: A Variational Analysis Perspective with Applications to Compressed Sensing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6148354)
