arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.04140cs.LGcs.SYeess.SYmath.OCstat.ML
收藏

具有通信保证的网络线性回归

Linear Regression over Networks with Communication Guarantees

University of Oxford(牛津大学)

Konstantinos Gatsis

摘要:

智能城市、智能交通系统和工业物联网等新兴互联自治系统的一个关键功能是能够处理和学习在不同物理位置收集的数据。在分布式学习和联邦学习的术语下,这越来越引起人们的关注。然而,在连接的自治系统中,数据传输通过通常具有有限资源的通信网络进行。本文探讨了利用数据的信息性进行线性回归任务的通信有效学习的算法。所开发的算法能够在通信和学习之间进行权衡,具有理论性能保证和有效的实际实现。

英文摘要:

A key functionality of emerging connected autonomous systems such as smart cities, smart transportation systems, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations. This is increasingly attracting attention under the terms of distributed learning and federated learning. However, in connected autonomous systems, data transfer takes place over communication networks with often limited resources. This paper examines algorithms for communication-efficient learning for linear regression tasks by exploiting the informativeness of the data. The developed algorithms enable a tradeoff between communication and learning with theoretical performance guarantees and efficient practical implementations.

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。

↑