Adaptive distributed methods under communication constraints

DOI10.1214/19-AOS1890zbMATH Open1455.62097MaRDI QIDQ2215741FDOQ2215741

Authors Harry van Zanten, Botond Szabó

Publication date 14 December 2020

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

Full work available at URL https://arxiv.org/abs/1804.00864

zbMATH Keywords

nonparametric regressionadaptationminimax ratescommunication constraintsdistributed computation

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Minimax procedures in statistical decision theory (62C20)

Abstract: We study distributed estimation methods under communication constraints in a distributed version of the nonparametric random design regression model. We derive minimax lower bounds and exhibit methods that attain those bounds. Moreover, we show that adaptive estimation is possible in this setting.

Recommendations

• Distributed nonparametric function estimation: optimal rate of convergence and cost of adaptation
• Communication lower bounds for statistical estimation problems via a distributed data processing inequality
• An asymptotic analysis of distributed nonparametric methods
• Distributed sparse normal means estimation with sublinear communication
• Distributed estimation and quantization

Cites work

• A Scalable Bootstrap for Massive Data
• Adaptive estimation of the transition density of a particular hidden Markov chain
• An asymptotic analysis of distributed nonparametric methods
• Communication-efficient sparse regression
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Distributed testing and estimation under sparse high dimensional models
• Honest and adaptive confidence sets in \(L_p\)
• Information-theoretic determination of minimax rates of convergence
• Introduction to nonparametric estimation
• Mathematical foundations of infinite-dimensional statistical models
• On the Sum Rate of Gaussian Multiterminal Source Coding: New Proofs and Results
• On the optimality of averaging in distributed statistical learning
• PenalizationversusGoldenshluger − Lepski strategies in warped bases regression
• Quantized minimax estimation over Sobolev ellipsoids
• Wavelets, approximation, and statistical applications

Cited in

(15)

• Distributed sparse normal means estimation with sublinear communication
• Distributed linear regression by averaging
• Communication lower bounds for statistical estimation problems via a distributed data processing inequality
• Distributed nonparametric function estimation: optimal rate of convergence and cost of adaptation
• On lower bounds for the bias-variance trade-off
• Quantized minimax estimation over Sobolev ellipsoids
• Distributed Decision-Making Over Adaptive Networks
• Learning Theory
• Optimal high-dimensional and nonparametric distributed testing under communication constraints
• Nonparametric Bayesian aggregation for massive data
• Consistency in models for distributed learning under communication constraints
• Distributed adaptive consensus protocol with decaying gains
• An asymptotic analysis of distributed nonparametric methods
• Distributed function estimation: adaptation using minimal communication
• Distributed adaptive Gaussian mean estimation with unknown variance: interactive protocol helps adaptation

This page was built for publication: Adaptive distributed methods under communication constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215741)