BriefGPT.xyz
Jul, 2023
解决联邦学习中的计算异构性：几个理论思路
Tackling Computational Heterogeneity in FL: A Few Theoretical Insights
HTML
PDF
Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis
TL;DR
机器学习的未来在于边缘计算，用于数据收集和训练，联邦学习是实现这一目标的一种方法。本文提出了一种新的聚合框架，用于解决联邦优化中的计算异构性问题，包括异构数据和本地更新，并从理论和实验的角度进行了广泛的分析。
Abstract
The future of
machine learning
lies in moving data collection along with training to the edge.
federated learning
, for short FL, has been recently proposed to achieve this goal. The principle of this approach is
→