Adaptive distributed methods under communication constraints

DOI10.1214/19-AOS1890zbMATH Open1455.62097arXiv1804.00864MaRDI QIDQ2215741FDOQ2215741

Authors: Harry van Zanten, Botond Szabó 

Publication date: 14 December 2020

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

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.

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

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

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)

Cites Work

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

Cited In (15)

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

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)