The _2,q regularized group sparse optimization: lower bound theory, recovery bound and algorithms
This paper deals with the classical problem of signal recovery, namely to restore a vector \(x^{0}\in \mathbb{R}^{N}\) from a noisy observation \(d\). This problem is modeled as \(d=Ax^0+\xi\) where \(A\in \mathbb{R}^{M\times N}\) is the measurement matrix and \(\xi \in \mathbb{R}^M\) represents the measurement error. The authors consider the case where the data to be restored have a natural structure. In particular, they assume that vectors \(x=(x_1,x_2,\ldots ,x_N)\in \mathbb{R}^N\) have a predefined group structure \(x=(x_{\mathcal{G}_1},x_{\mathcal{G}_2},\ldots ,x_{\mathcal{G}_n}),\) where \(\mathcal{G}_i\subset \{1,\ldots ,n\}\) and \(x_{\mathcal{G}_i}\) denotes the \(i\)-th group of \(x\) for \(i\in \{1,2,\ldots,n\}\). In this case, the group sparsity of \(x\) is better measured by a nonconvex \(\ell _{p,q}\) ``norm, defined by \(||x||_{p,q}:=\left( \sum_{i=1}^n ||x_{\mathcal{G}i}||_p^q \right)^{1/q},\) where \(p\geq 1\) and \(q\in (0,1)\). The authors consider the case \(p=2\) and focus on the minimization of the \(\ell _{p,q}\) regularization: \( \underset{x\in \mathbb{R}^{N}}{\mathrm{min}}\,\left\{||Ax-d||^{2}+||x||_{2,q}^{q}\right\}.\) They provide sufficient conditions for stationary points to be local minimizers and give a uniform lower bound for nonzero groups of local minimizers. They also propose a new IRLS (iteratively reweighted least square) algorithm with thresholding together with an error bound analysis. This new algorithm compares favorably with the classical IRLS algorithm with smoothing in both global convergence and computational efficiency. The paper also contains some numerical experiments.
- Group sparse optimization via \(\ell_{p,q}\) regularization
- An efficient and globally convergent algorithm for \(\ell_{p,q} - \ell_r\) model in group sparse optimization
- Robust group lasso: model and recoverability
- Sparse recovery by the iteratively reweighted _1 algorithm for elastic _2-_q minimization
- scientific article; zbMATH DE number 6747340
- A new globally convergent algorithm for non-Lipschitz \(\ell_{p}-\ell_q\) minimization
- A sparse signal reconstruction perspective for source localization with sensor arrays
- An efficient and globally convergent algorithm for \(\ell_{p,q} - \ell_r\) model in group sparse optimization
- An iterative support shrinking algorithm for non-Lipschitz optimization in image restoration
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- An unconstrained \(\ell_q\) minimization with \(0<q\leq 1\) for sparse solution of underdetermined linear systems
- Analysis of multi-stage convex relaxation for sparse regularization
- Atomic decomposition by basis pursuit
- Clarke Subgradients of Stratifiable Functions
- Compressed sensing and best \(k\)-term approximation
- Compressed sensing of color images
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Decoding by Linear Programming
- Empirical Bayes Estimation of a Sparse Vector of Gene Expression Changes
- Error bounds for compressed sensing algorithms with group sparsity: A unified approach
- Geometric categories and o-minimal structures
- Group sparse optimization via \(\ell_{p,q}\) regularization
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 2208228 (Why is no real title available?)
- scientific article; zbMATH DE number 3371284 (Why is no real title available?)
- Improved iteratively reweighted least squares for unconstrained smoothed _q minimization
- Iterative thresholding for sparse approximations
- Iteratively reweighted least squares minimization for sparse recovery
- Lower bound theory of nonzero entries in solutions of _2-_p minimization
- Model Selection and Estimation in Regression with Grouped Variables
- On gradients of functions definable in o-minimal structures
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Recovery of sparsest signals via \(\ell^q \)-minimization
- Robust Recovery of Signals From a Structured Union of Subspaces
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Shifting Inequality and Recovery of Sparse Signals
- Simultaneous analysis of Lasso and Dantzig selector
- Sparsest solutions of underdetermined linear systems via \( \ell _q\)-minimization for \(0<q\leqslant 1\)
- Stable signal recovery from incomplete and inaccurate measurements
- The Group Lasso for Logistic Regression
- The restricted isometry property and its implications for compressed sensing
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Robust group lasso: model and recoverability
- An efficient and globally convergent algorithm for \(\ell_{p,q} - \ell_r\) model in group sparse optimization
- The \(\ell_{2,p}\) regularized total variation with overlapping group sparsity prior for image restoration with impulse noise
- Group sparse recovery in impulsive noise via alternating direction method of multipliers
- Convergence and stability analysis of iteratively reweighted least squares for noisy block sparse recovery
- Error bounds for compressed sensing algorithms with group sparsity: A unified approach
- Globally sparse and locally dense signal recovery for compressed sensing
- Lower bound theory of nonzero entries in solutions of _2-_p minimization
- scientific article; zbMATH DE number 7594592 (Why is no real title available?)
- A general non-Lipschitz infimal convolution regularized model: Lower bound theory and algorithm
- Difference-of-Convex Algorithms for a Class of Sparse Group \ell₀ Regularized Optimization Problems
- Group sparse optimization via \(\ell_{p,q}\) regularization
- Solving constrained nonsmooth group sparse optimization via group Capped-\(\ell_1\) relaxation and group smoothing proximal gradient algorithm
- Continuous exact relaxation and alternating proximal gradient algorithm for partial sparse and partial group sparse optimization problems
- Group sparse structural smoothing recovery: model, statistical properties and algorithm
- Joint sparse optimization: lower-order regularization method and application in cell fate conversion
- Generalized nonconvex nonsmooth four-directional total variation with overlapping group sparsity for image restoration
- Smoothing composite proximal gradient algorithm for sparse group Lasso problems with nonsmooth loss functions
- Non-Lipschitz variational models and their iteratively reweighted least squares algorithms for image denoising on surfaces
- Iteratively reweighted least squares for block sparse signal recovery with unconstrained \(l_{2,p}\) minimization
- Non-Lipschitz attack: a more sparse adversarial attack via non-Lipschitz _p regularization
- Computing the proximal operator of the \(q\)-th power of the \(\ell_{1,q} \)-norm for group sparsity
- A general non-Lipschitz joint regularized model for multi-channel/modality image reconstruction
- Recovery bounds for cardinality regularized optimization problem
This page was built for publication: The \(\ell_{2,q}\) regularized group sparse optimization: lower bound theory, recovery bound and algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q778013)
