Resilient Distributed Optimization for Multi-Agent Cyberphysical Systems
Resilient Distributed Optimization for Multi-Agent Cyberphysical Systems
复制标题
DOI：
10.48550/arxiv.2212.02459
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
M. Yemini;Angelia Nedi'c;A. Goldsmith;Stephanie Gil
中科院分区：
文献类型：
--
作者：
M. Yemini;Angelia Nedi'c;A. Goldsmith;Stephanie Gil
这项工作的重点是在多代理网络物理系统中的分布式优化问题，其中一个合法的代理的迭代都受到潜在的恶意相邻代理的值，并通过自己的自我服务的目标函数。我们开发了一个新的算法和分析框架，以实现弹性的一类问题，其中代理之间的信任的随机值存在，并可以利用。在这种情况下，我们表明，收敛到真正的全局最优点可以恢复，无论是在平均值和几乎肯定，即使在恶意代理的存在。此外，我们提供了预期的收敛速度保证的形式上界的预期平方距离的最优值。最后，数值结果验证了我们的分析收敛保证，即使恶意代理组成的大多数代理在网络中，现有的方法无法收敛到最佳标称点。
This work focuses on the problem of distributed optimization in multi-agent cyberphysical systems, where a legitimate agents' iterates are influenced both by the values it receives from potentially malicious neighboring agents, and by its own self-serving target function. We develop a new algorithmic and analytical framework to achieve resilience for the class of problems where stochastic values of trust between agents exist and can be exploited. In this case we show that convergence to the true global optimal point can be recovered, both in mean and almost surely, even in the presence of malicious agents. Furthermore, we provide expected convergence rate guarantees in the form of upper bounds on the expected squared distance to the optimal value. Finally, numerical results are presented that validate our analytical convergence guarantees even when the malicious agents compose the majority of agents in the network and where existing methods fail to converge to the optimal nominal points.