A distributed one-step estimator
From MaRDI portal
Abstract: Distributed statistical inference has recently attracted enormous attention. Many existing work focuses on the averaging estimator. We propose a one-step approach to enhance a simple-averaging based distributed estimator. We derive the corresponding asymptotic properties of the newly proposed estimator. We find that the proposed one-step estimator enjoys the same asymptotic properties as the centralized estimator. The proposed one-step approach merely requires one additional round of communication in relative to the averaging estimator; so the extra communication burden is insignificant. In finite sample cases, numerical examples show that the proposed estimator outperforms the simple averaging estimator with a large margin in terms of the mean squared errors. A potential application of the one-step approach is that one can use multiple machines to speed up large scale statistical inference with little compromise in the quality of estimators. The proposed method becomes more valuable when data can only be available at distributed machines with limited communication bandwidth.
Recommendations
- Distributed linear regression by averaging
- First-Order Newton-Type Estimator for Distributed Estimation and Inference
- Distributed statistical inference for massive data
- Communication-efficient distributed estimator for generalized linear models with a diverging number of covariates
- Communication-efficient algorithms for statistical optimization
Cites work
- A split-and-conquer approach for analysis of
- Asymptotic Statistics
- Atomic Decomposition by Basis Pursuit
- Communication-efficient algorithms for statistical optimization
- Communication-efficient distributed statistical inference
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 204193 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Lectures on Stochastic Programming
- On the optimality of averaging in distributed statistical learning
- On the subspaces of \(L^p\) \((p > 2)\) spanned by sequences of independent random variables
- One-Step Huber Estimates in the Linear Model
- One-step Local Quasi-likelihood Estimation
- One-step sparse estimates in nonconcave penalized likelihood models
Cited in
(51)- Circumventing superefficiency: an effective strategy for distributed computing in non-standard problems
- A partitioned quasi-likelihood for distributed statistical inference
- Robust distributed modal regression for massive data
- Distributed one-step upgraded estimation for non-uniformly and non-randomly distributed data
- Distributed kernel ridge regression with communications
- Econometrics with privacy preservation
- One-Step Estimation with Scaled Proximal Methods
- Distributed estimation with empirical likelihood
- Divide and conquer for accelerated failure time model with massive time‐to‐event data
- Subsampling and Jackknifing: A Practically Convenient Solution for Large Data Analysis With Limited Computational Resources
- First-Order Newton-Type Estimator for Distributed Estimation and Inference
- Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous Data
- Distributed statistical inference for linear models with multi-source massive heterogeneous data
- A communication efficient distributed one-step estimation
- Design of distributed BFGS algorithm and large sample properties for parameter estimation
- Communication-efficient distributed estimation for high-dimensional large-scale linear regression
- LIC criterion for optimal subset selection in distributed interval estimation
- Model checking for parametric single-index models with massive datasets
- Distributed statistical optimization for non-randomly stored big data with application to penalized learning
- Residual projection for quantile regression in vertically partitioned big data
- Distributed SGD in overparametrized linear regression
- Distributed optimal subsampling for quantile regression with massive data
- Distributed subsampling for multiplicative regression
- The COR criterion for optimal subset selection in distributed estimation
- Distributed estimation and inference for semiparametric binary response models
- A selective review on statistical methods for massive data computation: distributed computing, subsampling, and minibatch techniques
- Support vector machine in big data: smoothing strategy and adaptive distributed inference
- Adaptive distributed inference for multi-source massive heterogeneous data
- Distributed parameter estimation framework based on moment method
- Distributed robust estimation and inference with contaminated data
- Communication-efficient distributed composite quantile regression via convolution smoothing and Poisson subsampling
- Enhancements of communication-efficient distributed statistical inference and its privacy preservation
- The ``component debiasing method in distributed Byzantine problems
- Optimal distributed subsampling for accelerated failure time models with massive censored data
- Grid Point Approximation for Distributed Nonparametric Smoothing and Prediction
- Federated Adaptive Causal Estimation (FACE) of Target Treatment Effects
- CluBear: a subsampling package for interactive statistical analysis with massive data on a single machine
- Privacy-preserving estimation for non-randomly distributed data
- Analyzing the dissemination of news by model averaging and subsampling
- Adaptive distributed smooth composite quantile regression estimation for large-scale data
- A Simple Divide-and-Conquer-based Distributed Method for the Accelerated Failure Time Model
- Distributed Heterogeneity Learning for Generalized Partially Linear Models with Spatially Varying Coefficients
- Novel closed-form point estimators for the beta distribution
- Accelerated distributed expectation-maximization algorithms for the parameter estimation in multivariate Gaussian mixture models
- Relative error-based distributed estimation in growing dimensions
- Composite quantile regression for a distributed system with non-randomly distributed data
- Communication-efficient distributed EM algorithm
- Communication-Efficient Pilot Estimation for Non-Randomly Distributed Data in Diverging Dimensions
- Byzantine-Robust Distributed One-Step Estimation
- Distributed high-dimensional quantile regression with the elastic net
- Communication-efficient distributed estimator for generalized linear models with a diverging number of covariates
This page was built for publication: A distributed one-step estimator
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1739027)
