异步梯度-推送
Asynchronous Gradient-Push
AI总结：
该研究提出了一种异步梯度-推送算法，用于分布式优化问题，该算法在多智能体网络中实现参数共识，证明了在强凸性和Lipschitz连续梯度条件下，异步操作能收敛到全局最小值的邻域，并通过数值实验展示了其在速度、鲁棒性和扩展性方面的优势。
摘要：
我们考虑了一个多智能体框架用于分布式优化，其中每个智能体都有一个局部的光滑强凸函数，集体目标是达成对最小化所有智能体局部函数总和的参数的一致性。我们提出了一种算法，其中每个智能体异步且独立地操作。当局部函数是强凸且梯度Lipschitz连续时，我们证明每个智能体的迭代过程收敛到全局最小值的邻域，邻域大小取决于多智能体网络中的异步程度。当所有智能体以相同速率工作时，可以收敛到全局极小值。数值实验表明，异步梯度-推送算法比最先进的同步一阶方法更快地最小化全局目标函数，对失败或停滞的智能体更具鲁棒性，并且在网络规模扩大时表现更好。
英文摘要：
We consider a multi-agent framework for distributed optimization where each agent has access to a local smooth strongly convex function, and the collective goal is to achieve consensus on the parameters that minimize the sum of the agents' local functions. We propose an algorithm wherein each agent operates asynchronously and independently of the other agents. When the local functions are strongly-convex with Lipschitz-continuous gradients, we show that the iterates at each agent converge to a neighborhood of the global minimum, where the neighborhood size depends on the degree of asynchrony in the multi-agent network. When the agents work at the same rate, convergence to the global minimizer is achieved. Numerical experiments demonstrate that Asynchronous Gradient-Push can minimize the global objective faster than state-of-the-art synchronous first-order methods, is more robust to failing or stalling agents, and scales better with the network size.
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。
