论文标题
分布式随机近似结合的浓度
A Concentration Bound for Distributed Stochastic Approximation
论文作者
论文摘要
我们重新审视Tsitsiklis，Bertsekas和Athans的经典模型，以通过共识分布式随机近似。主要的结果是使用ODE方法进行随机近似的方法对该方案进行了分析，从而导致高概率与适当插值迭代和限制微分方程之间的跟踪误差结合。未来的几个方向也将得到强调。
We revisit the classical model of Tsitsiklis, Bertsekas and Athans for distributed stochastic approximation with consensus. The main result is an analysis of this scheme using the ODE approach to stochastic approximation, leading to a high probability bound for the tracking error between suitably interpolated iterates and the limiting differential equation. Several future directions will also be highlighted.
