论文标题
拜占庭有弹性分散的随机优化，具有鲁棒的聚合规则
Byzantine-Resilient Decentralized Stochastic Optimization with Robust Aggregation Rules
论文作者
论文摘要
本文着重于在存在拜占庭攻击的情况下分散的随机优化。在优化过程中，称为拜占庭式工人的故障或恶意工人数量未知，不服从算法协议，并将任意错误的消息发送给其邻居。即使已经开发了各种拜占庭式弹性算法，以通过中央服务器进行分布式随机优化，但我们表明，当应用于分散的方案时，现有强大的聚合规则中存在两个主要问题：分散性和非差异和非二线随机杂音矩阵。本文提供了全面的分析，该分析揭示了这两个问题的负面影响，并提供了设计有利的拜占庭分散的随机优化算法的指南。根据这些准则，我们提出了迭代异常剪刀（iOS），这是一项基于迭代过滤的稳健聚合规则，具有可证明的性能保证。数值实验证明了iOS的有效性。仿真实现守则可在github.com/zhaoxian-wu/ios上获得。
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.
