Large-scale optimization problems that seek sparse solutions have become ubiquitous.
They are routinely solved with various specialized first-order methods. Although such …

We establish risk bounds for Regularized Empirical Risk Minimizers (RERM) when the loss
is Lipschitz and convex and the regularization function is a norm. In a first part, we obtain …

Extreme learning machine (ELM) as an emerging branch of machine learning has shown its
good generalization performance at a very fast learning speed. Nevertheless, the …

The breakthrough ideas in the modern proximal splitting methodologies allow us to express
the set of all minimizers of a superposition of multiple nonsmooth convex functions as the …

Interior point methods (IPMs) constitute one of the most important classes of optimization
methods, due to their unparalleled robustness, as well as their generality. It is well known …

This study examines the relatively recent development of a “fixed-point proximity” approach
to one type of minimization problem, considers its application to image denoising, and …

In this thesis, we develop a framework for reducing the dimensionality of composite
optimization problems using sparsity inducing regularizers. Based on the identification …

In this thesis, we develop a framework to reduce the dimensionality of composite
optimization problems with sparsity inducing regularizers. Based on the identification …