Adaptive fast gradient method in stochastic optimization tasks
Optimization and Control
2017-12-04 v1
Abstract
In this paper, we describe a stochastic adaptive fast gradient descent method based on the mirror variant of similar triangles method. To our knowledge, this is the first attempt to use adaptivity in stochastic method. Additionally, a main result was proved in terms of probabilities of large deviations.
Cite
@article{arxiv.1712.00062,
title = {Adaptive fast gradient method in stochastic optimization tasks},
author = {Alexander Tyurin},
journal= {arXiv preprint arXiv:1712.00062},
year = {2017}
}
Comments
in Russian