Split LBI: An Iterative Regularization Path with Structural Sparsity
نویسندگان
چکیده
An iterative regularization path with structural sparsity is proposed in this paper based on variable splitting and the Linearized Bregman Iteration, hence called Split LBI. Despite its simplicity, Split LBI outperforms the popular generalized Lasso in both theory and experiments. A theory of path consistency is presented that equipped with a proper early stopping, Split LBI may achieve model selection consistency under a family of Irrepresentable Conditions which can be weaker than the necessary and sufficient condition for generalized Lasso. Furthermore, some `2 error bounds are also given at the minimax optimal rates. The utility and benefit of the algorithm are illustrated by applications on both traditional image denoising and a novel example on partial order ranking.
منابع مشابه
Image Reconstruction for Diffuse Optical Tomography Based on Radiative Transfer Equation
Diffuse optical tomography is a novel molecular imaging technology for small animal studies. Most known reconstruction methods use the diffusion equation (DA) as forward model, although the validation of DA breaks down in certain situations. In this work, we use the radiative transfer equation as forward model which provides an accurate description of the light propagation within biological med...
متن کاملFast Splitting-Based Ordered-Subsets X-Ray CT Image Reconstruction
Using non-smooth regularization in X-ray computed tomography (CT) image reconstruction has become more popular these days due to the recent resurgence of the classic augmented Lagrangian (AL) methods in fields such as totalvariation (TV) denoising and compressed sensing (CS). For example, undersampling projection views is one way to reduce radiation dose in CT scans; however, this causes strong...
متن کاملGSplit LBI: Taming the Procedural Bias in Neuroimaging for Disease Prediction
In voxel-based neuroimage analysis, lesion features have been the main focus in disease prediction due to their interpretability with respect to the related diseases. However, we observe that there exists another type of features introduced during the preprocessing steps and we call them “Procedural Bias”. Besides, such bias can be leveraged to improve classification accuracy. Nevertheless, mos...
متن کاملSolving Structured Sparsity Regularization with Proximal Methods
Proximal methods have recently been shown to provide effective optimization procedures to solve the variational problems defining the !1 regularization algorithms. The goal of the paper is twofold. First we discuss how proximal methods can be applied to solve a large class of machine learning algorithms which can be seen as extensions of !1 regularization, namely structured sparsity regularizat...
متن کاملAn Iterative Algorithm for Nonlinear Inverse Problems with Joint Sparsity Constraints in Vector Valued Regimes and an Application to Color Image Inpainting
This paper is concerned with nonlinear inverse problems where data and solution are vector valued and, moreover, where the solution is assumed to have a sparse expansion with respect to a preassigned frame. We especially focus on such problems where the different components of the solution exhibit a common or so–called joint sparsity pattern. Joint sparsity means here that the measure (typicall...
متن کامل