On the optimality of averaging in distributed statistical learning

DOI10.1093/imaiai/iaw013zbMath1426.68241arXiv1407.2724OpenAlexW3103741939MaRDI QIDQ4606521

Boaz Nadler, Jonathan D. Rosenblatt

Publication date: 8 March 2018

Published in: Information and Inference (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1407.2724

zbMATH Keywords

distributed algorithmsmachine learningbig dataM-estimationempirical risk minimizationhigh-order asymptotics

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Distributed algorithms (68W15) Statistical aspects of big data and data science (62R07) Computational aspects of data analysis and big data (68T09)

Related Items (31)

A review of distributed statistical inference ⋮ Distributed optimization and statistical learning for large-scale penalized expectile regression ⋮ Robust distributed estimation and variable selection for massive datasets via rank regression ⋮ WONDER: Weighted one-shot distributed ridge regression in high dimensions ⋮ Distributed testing and estimation under sparse high dimensional models ⋮ Distributed kernel gradient descent algorithm for minimum error entropy principle ⋮ Communication-Efficient Distributed Linear Discriminant Analysis for Binary Classification ⋮ Averaging versus voting: a comparative study of strategies for distributed classification ⋮ Global debiased DC estimations for biased estimators via pro forma regression ⋮ Multivariate survival analysis in big data: A divide‐and‐combine approach ⋮ Model aggregation for doubly divided data with large size and large dimension ⋮ Robust distributed multicategory angle-based classification for massive data ⋮ Unnamed Item ⋮ A communication efficient distributed one-step estimation ⋮ Communication-efficient distributed estimation for high-dimensional large-scale linear regression ⋮ Communication-Efficient Accurate Statistical Estimation ⋮ Distributed function estimation: adaptation using minimal communication ⋮ Unnamed Item ⋮ Adaptive distributed methods under communication constraints ⋮ LIC criterion for optimal subset selection in distributed interval estimation ⋮ Unnamed Item ⋮ A distributed one-step estimator ⋮ Robust communication-efficient distributed composite quantile regression and variable selection for massive data ⋮ Distributed one-step upgraded estimation for non-uniformly and non-randomly distributed data ⋮ Unnamed Item ⋮ Communication-Efficient Distributed Eigenspace Estimation ⋮ Unnamed Item ⋮ Distributed statistical estimation and rates of convergence in normal approximation ⋮ Distributed linear regression by averaging ⋮ Distributed adaptive Huber regression ⋮ Unnamed Item

Uses Software

• MapReduce
• Hadoop
• Spark

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Geometric median and robust estimation in Banach spaces
• The price of bias reduction when there is no unbiased estimate
• The second-order bias and mean squared error of nonlinear estimators
• Robust regression: Asymptotics, conjectures and Monte Carlo
• Piecewise linear regularized solution paths
• On robust regression with high-dimensional predictors
• Asymptotic Statistics
• Understanding Machine Learning

This page was built for publication: On the optimality of averaging in distributed statistical learning