Description
In recent years, the amount of available information has become so
vast in certain fields of applications that it is infeasible or
undesirable to carry out the computations on a single server. This has
motivated the design and study of distributed statistical or learning
methods. In distributed methods, the data is split amongst different
administrative units and computations are carried out locally in
parallel to each other. The outcome of the local computations are then
aggregated into a final result on a central machine.
First, we will compare the theoretical properties of various
(Bayesian) distributed methods proposed in the literature on the
benchmark signal in Gaussian white noise model. Then we consider the
limitations and guarantees of distributed methods in general under
communication constraints on the same benchmark nonparametric model.
This is an ongoing joint work with Harry van Zanten.