An asymptotic analysis of distributed nonparametric methods
This work addresses performance analysis for distributed learning methods, but it is incremental as it focuses on theoretical comparison without introducing new methods.
The paper analyzed the performance of distributed nonparametric methods in a signal-in-Gaussian-white-noise model, finding that design and tuning significantly affect convergence rates and uncertainty quantification, and highlighting challenges in adapting to smoothness automatically.
We investigate and compare the fundamental performance of several distributed learning methods that have been proposed recently. We do this in the context of a distributed version of the classical signal-in-Gaussian-white-noise model, which serves as a benchmark model for studying performance in this setting. The results show how the design and tuning of a distributed method can have great impact on convergence rates and validity of uncertainty quantification. Moreover, we highlight the difficulty of designing nonparametric distributed procedures that automatically adapt to smoothness.