English

Adaptive Gradient Methods for Some Classes of Non-Smooth Optimization Problems

Optimization and Control 2020-08-25 v9

Abstract

We propose several adaptive algorithmic methods for problems of non-smooth convex optimization. The first of them is based on a special artificial inexactness. Namely, the concept of inexact (δ,Δ,L \delta, \Delta, L)-model of objective functional in optimization is introduced and some gradient-type methods with adaptation of inexactness parameters are proposed. A similar concept of an inexact model is introduced for variational inequalities as well as for saddle point problems. Analogues of switching sub-gradient schemes are proposed for convex programming problems with some general assumptions.

Keywords

Cite

@article{arxiv.1911.08425,
  title  = {Adaptive Gradient Methods for Some Classes of Non-Smooth Optimization Problems},
  author = {Fedor Stonyakin},
  journal= {arXiv preprint arXiv:1911.08425},
  year   = {2020}
}

Comments

in Russian

R2 v1 2026-06-23T12:21:00.618Z