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.

### Distributed function estimation: adaptation using minimal communication

#### Abstract

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.
##### Scheda breve Scheda completa Scheda completa (DC)
2022
Szabo, Botond; van Zanten, Harry
File in questo prodotto:
File
2003.12838.pdf

accesso aperto

Tipologia: Documento in Pre-print (Pre-print document)
Licenza: PUBBLICO DOMINIO
Dimensione 391.91 kB
Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11565/4052992