论文标题
梯度跟踪：一种平滑分布式优化的统一方法
Gradient Tracking: A Unified Approach to Smooth Distributed Optimization
论文作者
论文摘要
在这项工作中，我们研究了对挖掘的经典分布式优化问题，其中目标函数是平稳的局部函数的总和。受到我们早期工作中提出的隐式跟踪机制的启发，我们从纯原始的角度（即UGT）开发了统一的算法框架，该框架本质上是一种广义的梯度跟踪方法，可以统一具有恒定步骤尺寸的大多数现有的分布式优化算法。事实证明，如果全局目标函数强烈凸出，UGT的两个变体都可以实现线性收敛。最后，通过数值实验评估UGT的性能。
In this work, we study the classical distributed optimization problem over digraphs, where the objective function is a sum of smooth local functions. Inspired by the implicit tracking mechanism proposed in our earlier work, we develop a unified algorithmic framework from a pure primal perspective, i.e., UGT, which is essentially a generalized gradient tracking method and can unify most existing distributed optimization algorithms with constant step-sizes. It is proved that two variants of UGT can both achieve linear convergence if the global objective function is strongly convex. Finally, the performance of UGT is evaluated by numerical experiments.
