Convergence rates inℓ1-regularization if the sparsity assumption fails
From MaRDI portal
Publication:4917606
DOI10.1088/0266-5611/29/2/025013zbMATH Open1262.49010arXiv1209.5732OpenAlexW3103197010MaRDI QIDQ4917606FDOQ4917606
Bernd Hofmann, Jens Flemming, Martin Burger
Publication date: 2 May 2013
Published in: Inverse Problems (Search for Journal in Brave)
Abstract: Variational sparsity regularization based on -norms and other nonlinear functionals has gained enormous attention recently, both with respect to its applications and its mathematical analysis. A focus in regularization theory has been to develop error estimation in terms of regularization parameter and noise strength. For this sake specific error measures such as Bregman distances and specific conditions on the solution such as source conditions or variational inequalities have been developed and used. In this paper we provide, for a certain class of ill-posed linear operator equations, a convergence analysis that works for solutions that are not completely sparse, but have a fast decaying nonzero part. This case is not covered by standard source conditions, but surprisingly can be treated with an appropriate variational inequality. As a consequence the paper also provides the first examples where the variational inequality approach, which was often believed to be equivalent to appropriate source conditions, can indeed go farther than the latter.
Full work available at URL: https://arxiv.org/abs/1209.5732
Cited In (27)
- Convergence rates of Tikhonov regularization for recovering growth rates in a Lotka-Volterra competition model with diffusion
- Injectivity and \(\text{weak}^\star\)-to-weak continuity suffice for convergence rates in \(\ell^{1}\)-regularization
- Oversmoothing regularization with \(\ell^1\)-penalty term
- Variational smoothness assumptions in convergence rate theory -- an overview
- Flexible sparse regularization
- Existence of variational source conditions for nonlinear inverse problems in Banach spaces
- Multiscale scanning in inverse problems
- Optimal convergence rates for sparsity promoting wavelet-regularization in Besov spaces
- Convergence rates of Tikhonov regularizations for elliptic and parabolic inverse radiativity problems
- Sparsity regularization of the diffusion coefficient identification problem: well-posedness and convergence rates
- Convergence analysis of (statistical) inverse problems under conditional stability estimates
- Penalty-based smoothness conditions in convex variational regularization
- Variational source condition for ill-posed backward nonlinear Maxwell’s equations
- Tikhonov regularization with \({\ell^{0}}\)-term complementing a convex penalty: \({\ell^{1}}\)-convergence under sparsity constraints
- Regularization properties of the sequential discrepancy principle for Tikhonov regularization in Banach spaces
- Maximal spaces for approximation rates in \(\ell^1\)-regularization
- On ℓ 1 -Regularization Under Continuity of the Forward Operator in Weaker Topologies
- Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
- Convergence rates inℓ1-regularization when the basis is not smooth enough
- Modern regularization methods for inverse problems
- Fictitious null spaces for improving the solution of injective inverse problems
- Variational source conditions for inverse Robin and flux problems by partial measurements
- Variational source conditions and stability estimates for inverse electromagnetic medium scattering problems
- Elastic-net regularization versus ℓ 1 -regularization for linear inverse problems with quasi-sparse solutions
- Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
- Efficient regularization with wavelet sparsity constraints in photoacoustic tomography
- $ \newcommand{\e}{{\rm e}} {\alpha\ell_{1}-\beta\ell_{2}}$ regularization for sparse recovery
This page was built for publication: Convergence rates inℓ1-regularization if the sparsity assumption fails
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4917606)
