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 2206.04568cs.DC
收藏

具有鲁棒聚合规则的拜占庭弹性去中心化随机优化

Byzantine-Resilient Decentralized Stochastic Optimization with Robust Aggregation Rules

Zhaoxian Wu, Tianyi Chen, Qing Ling

AI总结:

本文针对去中心化随机优化中的拜占庭攻击问题,分析了现有鲁棒聚合规则存在的不一致性和非双随机虚拟混合矩阵两大缺陷,并提出具有性能保证的迭代离群值剪除(IOS)聚合规则。

摘要:

本文关注存在拜占庭攻击情况下的去中心化随机优化问题。在优化过程中,未知数量的故障或恶意工作节点(称为拜占庭工作节点)违反算法协议,并向其邻居发送任意错误消息。尽管针对带有中央服务器的分布式随机优化已经开发了多种拜占庭弹性算法,但我们表明,现有的鲁棒聚合规则在应用于去中心化场景时存在两个主要问题:不一致性和非双随机虚拟混合矩阵。本文提供了全面的分析,揭示了这两个问题的负面影响,并给出了设计良好的拜占庭弹性去中心化随机优化算法的指导原则。在这些指导原则下,我们提出了迭代离群值剪除(IOS),这是一种基于迭代过滤的鲁棒聚合规则,具有可证明的性能保证。数值实验证明了IOS的有效性。仿真实现代码可在github.com/Zhaoxian-Wu/IOS获取。

英文摘要:

This paper focuses on decentralized stochastic optimization in the presence of Byzantine attacks. During the optimization process, an unknown number of malfunctioning or malicious workers, termed as Byzantine workers, disobey the algorithmic protocol and send arbitrarily wrong messages to their neighbors. Even though various Byzantine-resilient algorithms have been developed for distributed stochastic optimization with a central server, we show that there are two major issues in the existing robust aggregation rules when being applied to the decentralized scenario: disagreement and non-doubly stochastic virtual mixing matrix. This paper provides comprehensive analysis that discloses the negative effects of these two issues, and gives guidelines of designing favorable Byzantine-resilient decentralized stochastic optimization algorithms. Under these guidelines, we propose iterative outlier scissor (IOS), an iterative filtering-based robust aggregation rule with provable performance guarantees. Numerical experiments demonstrate the effectiveness of IOS. The code of simulation implementation is available at github.com/Zhaoxian-Wu/IOS.

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。

↑