Universal composite prox-method for strictly convex optimization problems

TL;DR

This paper introduces a universal optimization method for strictly convex problems that extends Nesterov's approach using restart techniques and applies to general proximal setups beyond Euclidean spaces.

Contribution

It presents a novel universal method for strictly convex optimization that generalizes Nesterov's approach with restart techniques and flexible proximal setups.

Findings

Method effectively handles general proximal setups.

Achieves convergence for strictly convex problems.

Extends Nesterov's universal method to broader contexts.

Abstract

We propose a simple way to explain Univerasal method of Yu. Nesterov. Based on this method and using the restart technique we propose Universal method for strictly convex optimization problems. We consider general proximal set up (not necessarily euclidian one).