Robust Sparse Analysis Regularization
From MaRDI portal
Abstract: This paper investigates the theoretical guarantees of L1-analysis regularization when solving linear inverse problems. Most of previous works in the literature have mainly focused on the sparse synthesis prior where the sparsity is measured as the L1 norm of the coefficients that synthesize the signal from a given dictionary. In contrast, the more general analysis regularization minimizes the L1 norm of the correlations between the signal and the atoms in the dictionary, where these correlations define the analysis support. The corresponding variational problem encompasses several well-known regularizations such as the discrete total variation and the Fused Lasso. Our main contributions consist in deriving sufficient conditions that guarantee exact or partial analysis support recovery of the true signal in presence of noise. More precisely, we give a sufficient condition to ensure that a signal is the unique solution of the L1-analysis regularization in the noiseless case. The same condition also guarantees exact analysis support recovery and L2-robustness of the L1-analysis minimizer vis-a-vis an enough small noise in the measurements. This condition turns to be sharp for the robustness of the analysis support. To show partial support recovery and L2-robustness to an arbitrary bounded noise, we introduce a stronger sufficient condition. When specialized to the L1-synthesis regularization, our results recover some corresponding recovery and robustness guarantees previously known in the literature. From this perspective, our work is a generalization of these results. We finally illustrate these theoretical findings on several examples to study the robustness of the 1-D total variation and Fused Lasso regularizations.
Cited in
(32)- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- Sparse Regularization via Convex Analysis
- Maximal solutions of sparse analysis regularization
- Local behavior of sparse analysis regularization: applications to risk estimation
- A preconditioner for a primal-dual Newton conjugate gradient method for compressed sensing problems
- Guarantees of total variation minimization for signal recovery
- scientific article; zbMATH DE number 7312307 (Why is no real title available?)
- Boosting with structural sparsity: a differential inclusion approach
- Low complexity regularization of linear inverse problems
- Greedy-like algorithms for the cosparse analysis model
- Block-based refitting in \(\ell_{12}\) sparse regularization
- Exact support recovery for sparse spikes deconvolution
- Model selection with low complexity priors
- Sparsity-enforcing regularisation and ISTA revisited
- On the robustness of the generalized fused Lasso to prior specifications
- Exploiting low-rank structure in semidefinite programming by approximate operator splitting
- Robust Coordinate Descent Algorithm Robust Solution Path for High-dimensional Sparse Regression Modeling
- SPARSE AND ROBUST LINEAR REGRESSION: AN OPTIMIZATION ALGORITHM AND ITS STATISTICAL PROPERTIES
- Optimal dual certificates for noise robustness bounds in compressive sensing
- Cosparsity in Compressed Sensing
- Analysis _1-recovery with frames and Gaussian measurements
- \(\ell^1\)-analysis minimization and generalized (co-)sparsity: when does recovery succeed?
- Geometric properties of solutions to the total variation denoising problem
- Robust sparse principal component analysis: situation of full sparseness
- On uniqueness guarantees of solution in convex regularized linear inverse problems
- Modern regularization methods for inverse problems
- Gradient-based solution algorithms for a class of bilevel optimization and optimal control problems with a nonsmooth lower level
- Solution uniqueness of convex optimization problems via the radial cone
- Image reconstruction using analysis model prior
- The Geometry of Sparse Analysis Regularization
- Greedy signal space methods for incoherence and beyond
- Efficient regularization with wavelet sparsity constraints in photoacoustic tomography
This page was built for publication: Robust Sparse Analysis Regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2989297)
