Distributed statistical estimation and rates of convergence in normal approximation

DOI10.1214/19-EJS1647zbMATH Open1434.62046arXiv1704.02658MaRDI QIDQ2283576FDOQ2283576

Stanislav Minsker

Publication date: 3 January 2020

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: This paper presents a class of new algorithms for distributed statistical estimation that exploit divide-and-conquer approach. We show that one of the key benefits of the divide-and-conquer strategy is robustness, an important characteristic for large distributed systems. We establish connections between performance of these distributed algorithms and the rates of convergence in normal approximation, and prove non-asymptotic deviations guarantees, as well as limit theorems, for the resulting estimators. Our techniques are illustrated through several examples: in particular, we obtain new results for the median-of-means estimator, as well as provide performance guarantees for distributed maximum likelihood estimation.

Full work available at URL: https://arxiv.org/abs/1704.02658

zbMATH Keywords

normal approximationrobust estimationlimit theoremsmedian-of-means estimatordistributed estimation

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric robustness (62G35) Functional limit theorems; invariance principles (60F17)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximation Theorems of Mathematical Statistics
• Robust Estimation of a Location Parameter
• Estimates of Location Based on Rank Tests
• Probability Inequalities for Sums of Bounded Random Variables
• Note on the median of a multivariate distribution
• A Class of Statistics with Asymptotically Normal Distribution
• Geometric median and robust estimation in Banach spaces
• Challenging the empirical mean and empirical variance: a deviation study
• Loss minimization and parameter estimation with heavy tails
• Bandits With Heavy Tail
• Random generation of combinatorial structures from a uniform distribution
• On Some Robust Estimates of Location
• On statistics, computation and scalability
• A Berry–Esséen Bound for M‐estimators
• On the Medians of Gamma Distributions and an Equation of Ramanujan
• Sub-Gaussian mean estimators
• On the estimation of the mean of a random vector
• The Bahadur-Kiefer representation for \(U\)-quantiles
• Learning from untrusted data
• Robust and Scalable Bayes via a Median of Subset Posterior Measures
• Simple, scalable and accurate posterior interval estimation
• On the optimality of averaging in distributed statistical learning
• Sub-Gaussian estimators of the mean of a random vector
• Near-optimal mean estimators with respect to general norms
• Distributed estimation of principal eigenspaces

Cited In (21)

• LIC criterion for optimal subset selection in distributed interval estimation
• First-Order Newton-Type Estimator for Distributed Estimation and Inference
• Robust subgaussian estimation with VC-dimension
• Robust machine learning by median-of-means: theory and practice
• Distributed Bayesian inference in massive spatial data
• Discussion of the paper ‘A review of distributed statistical inference’
• Discussion of: ‘A review of distributed statistical inference’
• Distributed subsampling for multiplicative regression
• The COR criterion for optimal subset selection in distributed estimation
• Title not available (Why is that?)
• Byzantine-robust distributed sparse learning for \(M\)-estimation
• Nonparametric distributed learning under general designs
• Title not available (Why is that?)
• Robust classification via MOM minimization
• Robust and efficient mean estimation: an approach based on the properties of self-normalized sums
• Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous Data
• A review of distributed statistical inference
• Emerging directions in Bayesian computation
• Robust distributed multicategory angle-based classification for massive data
• Robust sub-Gaussian estimation of a mean vector in nearly linear time
• Large-Scale Inference of Multivariate Regression for Heavy-Tailed and Asymmetric Data

This page was built for publication: Distributed statistical estimation and rates of convergence in normal approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2283576)