论文标题
分布式平均估计和优化的相关量化
Correlated quantization for distributed mean estimation and optimization
论文作者
论文摘要
我们研究了在通信限制下的分布式平均估计和优化问题。我们提出了一个相关的量化协议，其误差保证中的主项取决于数据点的平均偏差，而不仅仅是它们的绝对范围。该设计不需要关于数据集的集中属性的任何先验知识，这需要在以前的工作中获得这种依赖。我们表明，在分布式优化算法中应用提出的协议作为子例程会导致更好的收敛速率。我们还证明了在轻度假设下我们的方案的最佳性。实验结果表明，我们提出的算法在各种任务上都优于现有的平均估计协议。
We study the problem of distributed mean estimation and optimization under communication constraints. We propose a correlated quantization protocol whose leading term in the error guarantee depends on the mean deviation of data points rather than only their absolute range. The design doesn't need any prior knowledge on the concentration property of the dataset, which is required to get such dependence in previous works. We show that applying the proposed protocol as sub-routine in distributed optimization algorithms leads to better convergence rates. We also prove the optimality of our protocol under mild assumptions. Experimental results show that our proposed algorithm outperforms existing mean estimation protocols on a diverse set of tasks.
