Communication-Efficient Distributed Statistical Inference
Communication-Efficient Distributed Statistical Inference
复制标题
DOI：
10.1080/01621459.2018.1429274
复制
发表时间：
2019-04-03
影响因子：
3.7
通讯作者：
Yang, Yun
中科院分区：
文献类型：
--
作者：
Jordan, Michael I.;Lee, Jason D.;Yang, Yun
我们提出了一个有效的通信代理似然（CSL）框架，用于解决分布式统计推断问题。CSL为全局可能性提供了一个通信高效的替代品，可用于低维估计、高维正则化估计和贝叶斯推理。对于低维估计，CSL可证明地改进了朴素平均方案，并有助于构造置信区间。对于高维正则化估计，CSL导致一个极小极大最优估计与控制通信成本。对于贝叶斯推断，CSL可用于形成收敛到真实后验的通信有效的准后验分布。这种准后验过程显着提高了马尔可夫链蒙特卡罗（MCMC）算法的计算效率，即使在非分布式设置。我们提出了理论分析和实验来探索CSL近似的属性。本文的补充材料可在网上查阅。
We present a communication-efficient surrogate likelihood (CSL) framework for solving distributed statistical inference problems. CSL provides a communication-efficient surrogate to the global likelihood that can be used for low-dimensional estimation, high-dimensional regularized estimation, and Bayesian inference. For low-dimensional estimation, CSL provably improves upon naive averaging schemes and facilitates the construction of confidence intervals. For high-dimensional regularized estimation, CSL leads to a minimax-optimal estimator with controlled communication cost. For Bayesian inference, CSL can be used to form a communication-efficient quasi-posterior distribution that converges to the true posterior. This quasi-posterior procedure significantly improves the computational efficiency of Markov chain Monte Carlo (MCMC) algorithms even in a nondistributed setting. We present both theoretical analysis and experiments to explore the properties of the CSL approximation. Supplementary materials for this article are available online.