Adaptive distributed methods under communication constraints

The Annals of Statistics, vol. 48

Abstract

We study 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.

Authors 2

1. Botond Szabó Aachen Mathematical Institute

   Leiden University

   Affiliation as printed

   Mathematical Institute , Leiden University ,

2. Harry van Zanten

   Vrije Universiteit Amsterdam

   Affiliation as printed

   Department of Mathematics , Faculty of Sciences , VU Amsterdam ,