English

Decentralized Saddle-Point Problems with Different Constants of Strong Convexity and Strong Concavity

Optimization and Control 2022-10-04 v2

Abstract

Large-scale saddle-point problems arise in such machine learning tasks as GANs and linear models with affine constraints. In this paper, we study distributed saddle-point problems (SPP) with strongly-convex-strongly-concave smooth objectives that have different strong convexity and strong concavity parameters of composite terms, which correspond to min and max variables, and bilinear saddle-point part. We consider two types of first-order oracles: deterministic (returns gradient) and stochastic (returns unbiased stochastic gradient). Our method works in both cases and takes several consensus steps between oracle calls.

Keywords

Cite

@article{arxiv.2206.00090,
  title  = {Decentralized Saddle-Point Problems with Different Constants of Strong Convexity and Strong Concavity},
  author = {Dmitriy Metelev and Alexander Rogozin and Alexander Gasnikov and Dmitry Kovalev},
  journal= {arXiv preprint arXiv:2206.00090},
  year   = {2022}
}