Distributed function estimation: adaptation using minimal communication (Q2694726): Difference between revisions
From MaRDI portal
Removed claim: author (P16): Item:Q335670 |
Changed an Item |
||
Property / author | |||
Property / author: Botond Szabó / rank | |||
Normal rank |
Revision as of 13:57, 13 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Distributed function estimation: adaptation using minimal communication |
scientific article |
Statements
Distributed function estimation: adaptation using minimal communication (English)
0 references
4 April 2023
0 references
Summary: We investigate whether in a distributed setting, adaptive estimation of a smooth function at the optimal rate is possible under minimal communication. It turns out that the answer depends on the risk considered and on the number of servers over which the procedure is distributed. We show that for the \(L_{\infty}\)-risk, adaptively obtaining optimal rates under minimal communication is not possible. For the \(L_2\)-risk, it is possible over a range of regularities that depends on the relation between the number of local servers and the total sample size.
0 references
divide-and-conquer methods
0 references
minimax rates
0 references
adaptation
0 references
communication constraints
0 references
Besov spaces
0 references
nonparametric estimation
0 references