Minimization of convex functionals over frame operators
نویسندگان
چکیده
منابع مشابه
Minimization of convex functionals over frame operators
We present results about minimization of convex functionals defined over a finite set of vectors in a finite dimensional Hilbert space, that extend several known results for the Benedetto-Fickus frame potential. Our approach depends on majorization techniques. We also consider some perturbation problems, where a positive perturbation of the frame operator of a set of vectors is realized as the ...
متن کاملMinimization of Error Functionals over Perceptron Networks
Supervised learning of perceptron networks is investigated as an optimization problem. It is shown that both the theoretical and the empirical error functionals achieve minima over sets of functions computable by networks with a given number n of perceptrons. Upper bounds on rates of convergence of these minima with n increasing are derived. The bounds depend on a certain regularity of training...
متن کاملOn the Minimization Problem of Sub-linear Convex Functionals
The study of the convergence to equilibrium of solutions to FokkerPlanck type equations with linear diffusion and super-linear drift leads in a natural way to a minimization problem for an energy functional (entropy) which relies on a sub-linear convex function. In many cases, conditions linked both to the non-linearity of the drift and to the space dimension allow the equilibrium to have a sin...
متن کاملMinimization of Non-smooth, Non-convex Functionals by Iterative Thresholding
Numerical algorithms for a special class of non-smooth and non-convex minimization problems in infinite dimensional Hilbert spaces are considered. The functionals under consideration are the sum of a smooth and non-smooth functional, both possibly non-convex. We propose a generalization of the gradient projection method and analyze its convergence properties. For separable constraints in the se...
متن کاملMinimization of Nonsmooth Convex Functionals in Banach Spaces
We develop a uniied framework for convergence analysis of subgradient and subgradient projection methods for minimization of nonsmooth convex functionals in Banach spaces. The important novel features of our analysis are that we neither assume that the functional is uniformly or strongly convex, nor use regularization techniques. Moreover, no boundedness assumptions are made on the level sets o...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Advances in Computational Mathematics
سال: 2008
ISSN: 1019-7168,1572-9044
DOI: 10.1007/s10444-008-9092-5