A review of distributed statistical inference

The rapid emergence of massive datasets in various fields poses a serious challenge to traditional statistical methods. Meanwhile, it provides opportunities for researchers develop novel algorithms. Inspired by the idea divide-and-conquer, distributed frameworks estimation and inference have been proposed. They were developed deal with large-scale optimization problems. This paper aims provide comprehensive review related literature. It includes parametric models, nonparametric other frequently used models. Their key ideas theoretical properties are summarized. trade-off between communication cost estimate precision together concerns discussed.