# An asymptotic analysis of distributed nonparametric methods

arXiv: https://arxiv.org/abs/1711.03149 · HTML: https://mlsanity.com/paper/1711.03149/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2017.

## Built on by (most cited first, 5 of 5)

- [Semiparametric inference using fractional posteriors](https://mlsanity.com/paper/2301.08158/) (2023)
- [Adaptive Resolution for Finite-Rank Gaussian Processes](https://mlsanity.com/paper/2505.24066/) (2025)
- [Gaussian Experts Selection using Graphical Models](https://mlsanity.com/paper/2102.01496/) (2021)
- [Information-Based Calibration of Uncertainty Quantification in Product-of-Experts Gaussian Process Models](https://mlsanity.com/paper/2608.29349/) (2026)
- [Entry Dependent Expert Selection in Distributed Gaussian Processes Using Multilabel Classification](https://mlsanity.com/paper/2211.09940/) (2022)

## Abstract (arXiv)

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.