Expected absolute value estimators for a spatially adapted regularization parameter choice rule
نویسندگان
چکیده
A total variation (TV) model with an L1-fidelity term and a spatially adapted regularization parameter is presented in order to reconstruct images contaminated by impulse noise. This model intends to preserve small details while homogeneous features still remain smooth. The regularization parameter is locally adapted according to a local expected absolute value estimator depending on the statistical characteristics of the noise. The numerical solution of the L1-TV minimization problem with a spatially adapted parameter is obtained by a superlinearly convergent algorithm based on Fenchel-duality and inexact semismooth Newton techniques, which is stable with respect to noise in the data. Numerical results justifying the advantage of such a regularization parameter choice rule are presented.
منابع مشابه
On Convergence of Kernel Learning Estimators
The paper studies kernel regression learning from stochastic optimization and ill-posedness point of view. Namely, the convergence properties of kernel learning estimators are investigated under a gradual elimination of the regularization parameter with rising number of observations. We derive computable non-asymptotic bounds on the deviation of the expected risk from its best possible value an...
متن کاملDistributionally Robust Groupwise Regularization Estimator
Regularized estimators in the context of group variables have been applied successfully in model and feature selection in order to preserve interpretability. We formulate a Distributionally Robust Optimization (DRO) problem which recovers popular estimators, such as Group Square Root Lasso (GSRL). Our DRO formulation allows us to interpret GSRL as a game, in which we learn a regression paramete...
متن کاملSpatially dependent regularization parameter selection in total generalized variation models for image restoration
The automated spatially dependent regularization parameter selection framework of [9] for multi-scale image restoration is applied to total generalized variation (TGV) of order two. Well-posedness of the underlying continuous models is discussed and an algorithm for the numerical solution is developed. Experiments confirm that due to the spatially adapted regularization parameter the method all...
متن کاملA new principle for choosing regularization parameter in certain inverse problems
A new parameter choice rule for inverse problems is introduced. This parameter choice rule was developed for total variation regularization in electron tomography and might in general be useful for L regularization of inverse problems with high levels of noise in the data.
متن کاملLarge-scale Inversion of Magnetic Data Using Golub-Kahan Bidiagonalization with Truncated Generalized Cross Validation for Regularization Parameter Estimation
In this paper a fast method for large-scale sparse inversion of magnetic data is considered. The L1-norm stabilizer is used to generate models with sharp and distinct interfaces. To deal with the non-linearity introduced by the L1-norm, a model-space iteratively reweighted least squares algorithm is used. The original model matrix is factorized using the Golub-Kahan bidiagonalization that proje...
متن کامل