论文标题
一种可靠的梯度跟踪方法，用于在有向网络上进行分布式优化
A Robust Gradient Tracking Method for Distributed Optimization over Directed Networks
论文作者
论文摘要
在本文中，我们考虑了具有指示网络拓扑的多代理网络上分布式共识优化的问题。假设每个代理都具有平稳且强烈凸的局部成本函数，则全球目标是最大程度地减少所有局部成本功能的平均值。为了解决该问题，我们引入了一种适用于最近提出的Push-Pull/AB算法的强大梯度跟踪方法（R-PUSH-PULL）。 R-Push-Pull继承了推扣的优势，并通过精确通信享受与最佳解决方案的线性收敛。在嘈杂的信息交换下，R-Push-Pull比现有的基于梯度跟踪算法更强大。在恒定的步进策略下，每个代理商获得的解决方案达到了最佳期望的最佳期望。我们提供了一个数字示例，以证明R-Push-Pull的有效性。
In this paper, we consider the problem of distributed consensus optimization over multi-agent networks with directed network topology. Assuming each agent has a local cost function that is smooth and strongly convex, the global objective is to minimize the average of all the local cost functions. To solve the problem, we introduce a robust gradient tracking method (R-Push-Pull) adapted from the recently proposed Push-Pull/AB algorithm. R-Push-Pull inherits the advantages of Push-Pull and enjoys linear convergence to the optimal solution with exact communication. Under noisy information exchange, R-Push-Pull is more robust than the existing gradient tracking based algorithms; the solutions obtained by each agent reach a neighborhood of the optimum in expectation exponentially fast under a constant stepsize policy. We provide a numerical example that demonstrate the effectiveness of R-Push-Pull.
