Open Access
Translator Disclaimer
2020 Nonparametric distributed learning under general designs
Meimei Liu, Zuofeng Shang, Guang Cheng
Electron. J. Statist. 14(2): 3070-3102 (2020). DOI: 10.1214/20-EJS1733


This paper focuses on the distributed learning in nonparametric regression framework. With sufficient computational resources, the efficiency of distributed algorithms improves as the number of machines increases. We aim to analyze how the number of machines affects statistical optimality. We establish an upper bound for the number of machines to achieve statistical minimax in two settings: nonparametric estimation and hypothesis testing. Our framework is general compared with existing work. We build a unified frame in distributed inference for various regression problems, including thin-plate splines and additive regression under random design: univariate, multivariate, and diverging-dimensional designs. The main tool to achieve this goal is a tight bound of an empirical process by introducing the Green function for equivalent kernels. Thorough numerical studies back theoretical findings.


Download Citation

Meimei Liu. Zuofeng Shang. Guang Cheng. "Nonparametric distributed learning under general designs." Electron. J. Statist. 14 (2) 3070 - 3102, 2020.


Received: 1 July 2019; Published: 2020
First available in Project Euclid: 21 August 2020

zbMATH: 07246813
MathSciNet: MR4137596
Digital Object Identifier: 10.1214/20-EJS1733

Primary: 62G08
Secondary: 62G10

Keywords: Computational limit , Divide and conquer , kernel ridge regression , Minimax optimality , Nonparametric testing


Vol.14 • No. 2 • 2020
Back to Top