多智能体信息物理系统的弹性分布式优化
Resilient Distributed Optimization for Multi-Agent Cyberphysical Systems
AI总结：
针对多智能体信息物理系统中恶意智能体干扰分布式优化的问题，提出基于随机信任值的弹性算法框架，证明均值与几乎必然收敛性，给出收敛速率上界，且在恶意智能体占多数时仍有效。
摘要：
本研究聚焦多智能体信息物理系统中的分布式优化问题，在这类系统中，合法智能体的迭代值既受其从潜在恶意相邻智能体接收的值的影响，也受自身自利目标函数的影响。我们提出了一种新的算法与分析框架，针对智能体间存在可利用的随机信任值的一类问题实现弹性。研究表明，即便存在恶意智能体，系统仍可恢复至真实全局最优点的收敛性，且在均值意义和几乎必然意义上均成立。此外，我们以到最优值的期望平方距离的上界形式，给出了期望收敛速率保证。最后，数值实验结果验证了我们的理论收敛保证，即便当恶意智能体占网络中大多数、现有方法无法收敛到标称最优点时，该方法依然有效。
英文摘要：
This work focuses on the problem of distributed optimization in multi-agent cyberphysical systems, where a legitimate agent's 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.
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。
