Generalized SURE for exponential families: applications to regularization

Authors:
Yonina C. Eldar
Affiliations:
Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel
Venue:
IEEE Transactions on Signal Processing
Year:
2009

Citing 9
Cited 7

Fundamentals of statistical signal processing: estimation theory

Fundamentals of statistical signal processing: estimation theory
The use of the L-curve in the regularization of discrete ill-posed problems

SIAM Journal on Scientific Computing
The “minimum reconstruction error” choice of regularization parameters: some more efficient methods and their application to deconvolution problems

SIAM Journal on Scientific Computing
Deblurring Images: Matrices, Spectra, and Filtering (Fundamentals of Algorithms 3) (Fundamentals of Algorithms)

Deblurring Images: Matrices, Spectra, and Filtering (Fundamentals of Algorithms 3) (Fundamentals of Algorithms)
Robust mean-squared error estimation in the presence of model uncertainties

IEEE Transactions on Signal Processing
Blind Minimax Estimation

IEEE Transactions on Information Theory
Bayesian and regularization methods for hyperparameter estimation in image restoration

IEEE Transactions on Image Processing
Building robust wavelet estimators for multicomponent images using Stein's principle

IEEE Transactions on Image Processing
A New SURE Approach to Image Denoising: Interscale Orthonormal Wavelet Thresholding

IEEE Transactions on Image Processing

Rethinking Biased Estimation: Improving Maximum Likelihood and the Cramér–Rao Bound

Foundations and Trends in Signal Processing
A SURE approach for digital signal/image deconvolution problems

IEEE Transactions on Signal Processing
Covariance estimation in decomposable Gaussian graphical models

IEEE Transactions on Signal Processing
Nonparametric cepstrum estimation via optimal risk smoothing

IEEE Transactions on Signal Processing
Least squares estimation without priors or supervision

Neural Computation
Classifier design given an uncertainty class of feature distributions via regularized maximum likelihood and the incorporation of biological pathway knowledge in steady-state phenotype classification

Pattern Recognition
Compressed sensing based on dictionary learning for extracting impulse components

Signal Processing

Quantified Score

Hi-index	35.69

Visualization

Abstract

Stein's unbiased risk estimate (SURE) was proposed by Stein for the independent, identically distributed (i.i.d.) Gaussian model in order to derive estimates that dominate least squares (LS). Recently, the SURE criterion has been employed in a variety of denoising problems for choosing regularization parameters that minimize an estimate of the mean-squared error (MSE). However, its use has been limited to the i.i.d. case which precludes many important applicatious. In this paper we begin by deriving a SURE counterpart for general, not necessarily i.i.d. distributions from the exponential family. This enables extending the SURE desigu technique to a much broader class of problems. Based on this generalization we suggest a new method for choosing regularization parameters in penalized LS estimators. We then demonstrate its superior performance over the conventional generalized cross validation and discrepancy approaches in the context of image deblurring and deconvolution. The SURE technique can also be used to design estimates without predefining their structure. However, allowing for too many free parameters impairs the estimate's performance. To address this inherent tradeoff, we propose a regularized SURE objective, and demonstrate its use in the context of wavelet denoising.