Orthogonal subsampling for big data linear regression

DOI10.1214/21-AOAS1462zbMath1478.62384arXiv2105.14647OpenAlexW3204212820MaRDI QIDQ2247473

Weng Kee Wong, Lin Wang, Hongquan Xu, Jake Elmstedt

Publication date: 17 November 2021

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.14647

zbMATH Keywords

data reductionorthogonal arrayoptimal designexperimental design

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Optimal statistical designs (62K05) Statistical aspects of big data and data science (62R07)

Related Items (7)

Information-based optimal subdata selection for non-linear models ⋮ Optimal subsampling design for polynomial regression in one covariate ⋮ Predictive Subdata Selection for Computer Models ⋮ Subdata selection based on orthogonal array for big data ⋮ Optimal sampling designs for multidimensional streaming time series with application to power grid sensor data ⋮ Optimal subsampling for least absolute relative error estimators with massive data ⋮ Model-free global likelihood subsampling for massive data

Uses Software

• UCI-ml
• glmnet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Recent developments in nonregular fractional factorial designs
• Optimal Bayesian design applied to logistic regression experiments
• Orthogonal arrays with variable numbers of symbols
• Orthogonal arrays. Theory and applications
• Divide-and-conquer information-based optimal subdata selection algorithm
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• A review of some exchange algorithms for constructing discrete \(D\)-optimal designs
• Construction of supersaturated designs through partially aliased interactions
• Columnwise-Pairwise Algorithms with Applications to the Construction of Supersaturated Designs
• On Computationally Tractable Selection of Experiments in Measurement-Constrained Regression Models
• Information-Based Optimal Subdata Selection for Big Data Linear Regression
• Regularization and Variable Selection Via the Elastic Net
• Exchange algorithms for constructing large spatial designs

This page was built for publication: Orthogonal subsampling for big data linear regression