Quantcast

Mirror Descent for Constrained Optimization Problems with Large Subgradient Values

Research paper by Fedor Stonyakin, Alexander Titov, Alexey Stepanov, Alexander Gasnikov

Indexed on: 07 Jul '20Published on: 01 Aug '19Published in: arXiv - Mathematics - Optimization and Control



Abstract

Based on the ideas of arXiv:1710.06612, we consider the problem of minimization of the Lipschitz-continuous non-smooth functional $f$ with non-positive convex (generally, non-smooth) Lipschitz-continuous functional constraint. We propose some novel strategies of step-sizes and adaptive stopping rules in Mirror Descent algorithms for the considered class of problems. It is shown that the methods are applicable to the objective functionals of various levels of smoothness. Applying the restart technique to the Mirror Descent Algorithm there was proposed an optimal method to solve optimization problems with strongly convex objective functionals. Estimates of the rate of convergence of the considered algorithms are obtained depending on the level of smoothness of the objective functional. These estimates indicate the optimality of considered methods from the point of view of the theory of lower oracle bounds. In addition, the case of a quasi-convex objective functional and constraint was considered.