Statistical Multiresolution Dantzig Estimation in Imaging: Fundamental Concepts and Algorithmic Framework
arXiv:1101.4373 · doi:10.1214/12-EJS671
Abstract
In this paper we are concerned with fully automatic and locally adaptive estimation of functions in a "signal + noise"-model where the regression function may additionally be blurred by a linear operator, e.g. by a convolution. To this end, we introduce a general class of statistical multiresolution estimators and develop an algorithmic framework for computing those. By this we mean estimators that are defined as solutions of convex optimization problems with supremum-type constraints. We employ a combination of the alternating direction method of multipliers with Dykstra's algorithm for computing orthogonal projections onto intersections of convex sets and prove numerical convergence. The capability of the proposed method is illustrated by various examples from imaging and signal detection.
References in corpus (8)
- Simultaneous analysis of Lasso and Dantzig selector
- Templates for Convex Cone Problems with Applications to Sparse Signal Recovery
- Consistencies and rates of convergence of jump-penalized least squares estimators
- Multiscale inference about a density
- Densities, spectral densities and modality
- Discussion: The Dantzig selector: Statistical estimation when is much larger than
- Residual-based localization and quantification of peaks in x-ray diffractograms
- Shape Constrained Regularisation by Statistical Multiresolution for Inverse Problems: Asymptotic Analysis
Cited by in corpus (12)
- A combined first and second order variational approach for image reconstruction
- Global Variational Method for Fingerprint Segmentation by Three-part Decomposition
- Controlled Wavelet Domain Sparsity in X-ray Tomography
- Variational Multiscale Nonparametric Regression: Smooth Functions
- A Globally Linearly Convergent Method for Pointwise Quadratically Supportable Convex-Concave Saddle Point Problems
- A Variational View on Statistical Multiscale Estimation
- Frame-constrained Total Variation Regularization for White Noise Regression
- Parallel Statistical Multi-resolution Estimation
- Shape Constrained Regularisation by Statistical Multiresolution for Inverse Problems: Asymptotic Analysis
- Variational Multiscale Nonparametric Regression: Algorithms and Implementation
- Local Linear Convergence of the ADMM/Douglas--Rachford Algorithms without Strong Convexity and Application to Statistical Imaging
- Statistical Multiresolution Estimation for Variational Imaging: With an Application in Poisson-Biophotonics