Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems. (arXiv:2304.10902v1 [math.OC])

Minimax optimization plays an important role in many machine learning tasks
such as generative adversarial networks (GANs) and adversarial training.
Although recently a wide variety of optimization methods have been proposed to
solve the minimax problems, most of them ignore the distributed setting where
the data is distributed on multiple workers. Meanwhile, the existing
decentralized minimax optimization methods rely on the strictly assumptions
such as (strongly) concavity and variational inequality conditions. In the
paper, thus, we propose an efficient decentralized …

arxiv assumptions data decentralized distributed gans gda generative generative adversarial networks gradient inequality machine machine learning math minimax multiple near networks optimization paper role training workers