论文标题
分布式原始二重性优化针对异质多代理系统
Distributed Primal-dual Optimization for Heterogeneous Multi-agent Systems
论文作者
论文摘要
在计算，存储和通信方面，异质网络包括具有不同功能的代理。在这种设置中，要考虑允许代理商选择适当更新方案的操作特性至关重要，以更好地分发计算任务并更有效地利用网络。我们考虑了合作最小化局部强烈凸目标总和的多代理优化问题。我们提出了一个异步分布式偶对偶的协议，该协议允许原始更新步骤与代理有关（代理可以在一阶或牛顿更新之间选择）。我们的分析介绍了这种混合优化方案的统一框架，并在强烈凸目标和一般代理激活方案下建立了期望中的全局线性收敛。现实生活数据集的数值实验证明了所提出的算法的优点。
Heterogeneous networks comprise agents with varying capabilities in terms of computation, storage, and communication. In such settings, it is crucial to factor in the operating characteristics in allowing agents to choose appropriate updating schemes, so as to better distribute computational tasks and utilize the network more efficiently. We consider the multi-agent optimization problem of cooperatively minimizing the sum of local strongly convex objectives. We propose an asynchronous distributed primal-dual protocol, which allows for the primal update steps to be agent-dependent (an agent can opt between first-order or Newton updates). Our analysis introduces a unifying framework for such hybrid optimization scheme and establishes global linear convergence in expectation, under strongly convex objectives and general agent activation schemes. Numerical experiments on real life datasets attest to the merits of the proposed algorithm.
