Adaptive distributed methods under communication constraints

Botond Szabó, Harry van Zanten

Research output: Contribution to JournalArticleAcademicpeer-review

21 Downloads (Pure)

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.

Original languageEnglish
Pages (from-to)2347-2380
Number of pages34
JournalAnnals of Statistics
Volume48
Issue number4
Early online date14 Aug 2020
DOIs
Publication statusPublished - Aug 2020

Funding

Acknowledgements. We would like to thank the Associate Editor and the referees for their careful review of the various versions of this paper and for their valuable comments and suggestions. Both authors were supported by the Netherlands Organization of Scientific Research NWO. The research leading to these results has received funding from the European Research Council under ERC Grant Agreement 320637.

FundersFunder number
Netherlands Organization of Scientific Research NWO
Seventh Framework Programme320637
European Research Council

    Keywords

    • Adaptation
    • Communication constraints
    • Distributed computation
    • Minimax rates
    • Nonparametric regression

    Fingerprint

    Dive into the research topics of 'Adaptive distributed methods under communication constraints'. Together they form a unique fingerprint.

    Cite this