COLA：分散式线性学习
COLA: Decentralized Linear Learning
摘要：
分散式机器学习是一个有前途的新兴范式，鉴于全球的数据所有权和隐私的挑战。我们考虑在训练数据分散在许多用户设备上的设置中学习线性分类和回归模型，并且学习算法必须在设备上运行，在任意通信网络上，没有中央协调器。我们提出了COLA，一种新的分散训练算法，具有强大的理论保证和优越的实际性能。我们的框架克服了现有方法的许多局限性，并实现了通信效率，可扩展性，弹性以及对数据和参与设备变化的弹性。
英文摘要：
Decentralized machine learning is a promising emerging paradigm in view of global challenges of data ownership and privacy. We consider learning of linear classification and regression models, in the setting where the training data is decentralized over many user devices, and the learning algorithm must run on-device, on an arbitrary communication network, without a central coordinator. We propose COLA, a new decentralized training algorithm with strong theoretical guarantees and superior practical performance. Our framework overcomes many limitations of existing methods, and achieves communication efficiency, scalability, elasticity as well as resilience to changes in data and participating devices.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
