Adaptive distributed methods under communication constraints
Botond Szabó, Harry van Zanten
The Annals of Statistics · 2020 · Volume 48 · Issue 4
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.
Keywords
62B10, 62G08, 62G20, Adaptation, communication constraints, Distributed computation, Minimax rates, Nonparametric regression
Enable JavaScript for citation tools and additional paper interactions.