论文标题
在线分散的Frank-Wolfe：从理论界限到智能构建的应用
Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building
论文作者
论文摘要
在快速增长的世界中，分散学习算法的设计很重要，在这个世界中，数据分布在本地计算资源和通信有限的参与者上。在这个方向上，我们提出了一种在线算法最小化从网络上分布的单个数据/模型汇总的非凸损失函数。我们提供算法的理论性能保证，并在现实生活中展示其实用性。
The design of decentralized learning algorithms is important in the fast-growing world in which data are distributed over participants with limited local computation resources and communication. In this direction, we propose an online algorithm minimizing non-convex loss functions aggregated from individual data/models distributed over a network. We provide the theoretical performance guarantee of our algorithm and demonstrate its utility on a real life smart building.
