arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2211.00533cs.LGmath.OC
收藏

时变网络中非凸分散学习的最优复杂性

Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks

University of Pennsylvania(宾夕法尼亚大学);Peking University(北京大学)

Xinmeng Huang, Kun Yuan

摘要:

时变网络的分散优化是机器学习中的一个新兴范例。它在大规模深度训练中节省了显着的通信开销,并且在无线场景中更鲁棒,特别是当节点移动时。联邦学习也可以被视为分散优化,具有在全局平均和局部更新之间交替的时变通信模式。虽然存在许多研究来澄清其理论限制并开发有效的算法,但仍不清楚时变网络上非凸分散随机优化的最佳复杂度是多少。主要困难在于如何衡量两个节点之间通过时变通信传输消息时的有效性,以及如何在网络规模固定时建立下限(这是随机优化的先决条件)。本文解决了这些挑战,并建立了第一个下界的复杂性。我们还开发了一个新的分散算法,几乎达到了下界,显示了下界的紧密性和我们的算法的最优性。

英文摘要:

Decentralized optimization with time-varying networks is an emerging paradigm in machine learning. It saves remarkable communication overhead in large-scale deep training and is more robust in wireless scenarios especially when nodes are moving. Federated learning can also be regarded as decentralized optimization with time-varying communication patterns alternating between global averaging and local updates. While numerous studies exist to clarify its theoretical limits and develop efficient algorithms, it remains unclear what the optimal complexity is for non-convex decentralized stochastic optimization over time-varying networks. The main difficulties lie in how to gauge the effectiveness when transmitting messages between two nodes via time-varying communications, and how to establish the lower bound when the network size is fixed (which is a prerequisite in stochastic optimization). This paper resolves these challenges and establish the first lower bound complexity. We also develop a new decentralized algorithm to nearly attain the lower bound, showing the tightness of the lower bound and the optimality of our algorithm.

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。

↑