论文标题
在一般假设下，分散SGD的加速度与随机噪声低的一般假设
An acceleration of decentralized SGD under general assumptions with low stochastic noise
论文作者
论文摘要
分布式优化方法由优化社区积极研究。由于在分布式机器学习中的应用，现代研究方向包括随机目标，降低通信频率以及随时间变化的通信网络拓扑。最近，在Koloskova等人中开发了一项分析，该分析统一了几种集中式和分散的随机分布式优化方法。 （2020）。在这项工作中，我们采用了催化剂框架，并加速了Koloskova等人的速度。 （2020）在低随机噪声的情况下。
Distributed optimization methods are actively researched by optimization community. Due to applications in distributed machine learning, modern research directions include stochastic objectives, reducing communication frequency, and time-varying communication network topology. Recently, an analysis unifying several centralized and decentralized approaches to stochastic distributed optimization was developed in Koloskova et al. (2020). In this work, we employ a Catalyst framework and accelerate the rates of Koloskova et al. (2020) in the case of low stochastic noise.
