Accelerated methods for composite non-bilinear saddle point problem
Optimization and Control
2020-01-03 v7
Abstract
Based on G. Lan's accelerated gradient sliding and general relation between the smoothness and strong convexity parameters of function under Legendre transformation we show that under rather general conditions the best known bounds for bilinear convex-concave smooth composite saddle point problem keep true for or non-bilinear convex-concave smooth composite saddle point problem. Moreover, we describe situations when the bounds differ and explain the nature of the difference.
Cite
@article{arxiv.1906.03620,
title = {Accelerated methods for composite non-bilinear saddle point problem},
author = {Mohammad Alkousa and Darina Dvinskikh and Fedor Stonyakin and Alexander Gasnikov and Dmitry Kovalev},
journal= {arXiv preprint arXiv:1906.03620},
year = {2020}
}
Comments
28 pages, in Russian