Stability of Minimizers of Regularized Least Squares Objective Functions Ii: Study of the Global Behavior
نویسنده
چکیده
We address estimation problems where the sought-after solution is defined as the minimizer of an objective function composed of a quadratic data-fidelity term and a regularization term. We especially focus on nonsmooth and/or nonconvex regularization terms because of their ability to yield good estimates. This work is dedicated to the stability of the minimizers of such nonsmooth and/or nonconvex objective functions. It is composed of two parts. In the previous part of this work, we considered general local minimizers. In this part, we derive results on global minimizers. We show that the data domain contains an open, dense subset such that for every data point therein, the objective function has a finite number of local minimizers, and a unique global minimizer which is stable under variations of the data.
منابع مشابه
Stability of Minimizers of Regularized Least Squares Objective Functions I: Study of the Local Behavior
Abstract. Many estimation problems amount to minimizing an objective function composed of a quadratic data-fidelity term and a general regularization term. It is widely accepted that the minimizers obtained using nonsmooth and/or nonconvex regularization terms are frequently good estimates. However, very few facts are known on the ways to control properties of these minimizers. This work is ded...
متن کاملCharacterizing Global Minimizers of the Difference of Two Positive Valued Affine Increasing and Co-radiant Functions
Many optimization problems can be reduced to a problem with an increasing and co-radiant objective function by a suitable transformation of variables. Functions, which are increasing and co-radiant, have found many applications in microeconomic analysis. In this paper, the abstract convexity of positive valued affine increasing and co-radiant (ICR) functions are discussed. Moreover, the ...
متن کاملGroup Sparse Recovery via the ℓ0(ℓ2) Penalty: Theory and Algorithm
In this work we propose and analyze a novel approach for recovering group sparse signals, which arise naturally in a number of practical applications. It is based on regularized least squares with an `(`) penalty. One distinct feature of the new approach is that it has the built-in decorrelation mechanism within each group, and thus can handle the challenging strong inner-group correlation. We ...
متن کاملA pr 2 01 3 Description of the minimizers of least squares regularized with l 0 - norm . Uniqueness of the global minimizer
We have an M × N real-valued arbitrary matrix A (e.g. a dictionary) with M < N and data d describing the sought-after object with the help of A. This work provides an indepth analysis of the (local and global) minimizers of an objective function Fd combining a quadratic data-fidelity term and an l0 penalty applied to each entry of the sought after solution, weighted by a regularization paramete...
متن کاملDescription of the minimizers of least squares regularized with l0-norm. Uniqueness of the global minimizer
We have an M × N real-valued arbitrary matrix A (e.g. a dictionary) with M < N and data d describing the sought-after object with the help of A. This work provides an in-depth analysis of the (local and global) minimizers of an objective function Fd combining a quadratic data-fidelity term and an l0 penalty applied to each entry of the sought-after solution, weighted by a regularization paramet...
متن کامل