On Convergence Analysis of Iterative Smoothing Methods for a Class of Nonsmooth Convex Minimization Problems

摘要

We consider the problem of minimizing a convex objective which is the sum of a smooth part and a non-smooth part. Inspired by various application, we focus on the case when the non-smooth part is a max function. In this paper, we consider to solve such problems using iterative smoothing-gradient methods. We conduct run-time complexity and convergence analysis of smoothing algorithms.