arxivst stuff from arxiv that you should probably bookmark

Distributed Statistical Estimation and Rates of Convergence in Normal Approximation

Abstract · Apr 9, 2017 20:43 ·

distributed guarantees median conquer characteristic nodes divide estimation robustness intermediate math-st cs-dc stat-ml stat-th

Arxiv Abstract

  • Stanislav Minsker
  • Nate Strawn

This paper presents new algorithms for distributed statistical estimation that can take advantage of the divide-and-conquer approach. We show that one of the key benefits attained by an appropriate divide-and-conquer strategy is robustness, an important characteristic of large distributed systems. We introduce a class of algorithms that are based on the properties of the geometric median, establish connections between performance of these distributed algorithms and rates of convergence in normal approximation, and provide tight deviations guarantees for resulting estimators in the form of exponential concentration inequalities. We illustrate our techniques with several examples; in particular, we obtain new results for the median-of-means estimator, as well as provide performance guarantees for robust distributed maximum likelihood estimation.

Read the paper (pdf) »