English

Communication-Efficient Distributed Statistical Inference

Machine Learning 2016-11-08 v3 Information Theory Machine Learning math.IT Optimization and Control Methodology

Abstract

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 MCMC algorithms even in a non-distributed setting. We present both theoretical analysis and experiments to explore the properties of the CSL approximation.

Keywords

Cite

@article{arxiv.1605.07689,
  title  = {Communication-Efficient Distributed Statistical Inference},
  author = {Michael I. Jordan and Jason D. Lee and Yun Yang},
  journal= {arXiv preprint arXiv:1605.07689},
  year   = {2016}
}
R2 v1 2026-06-22T14:08:50.476Z