Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over the data. We show that optimal generalization error bounds can be retained for distributed SGM provided that the partition level is not too large. Our results are superior to the state-of-the-art theory, covering the cases that the regression function may not be in the hypothesis spaces. Particularly, our results show that distributed SGM has a smaller theoretical computational complexity, compared with distributed kernel ridge regression (KRR) and classic SGM.


Publié dans:
Proceedings of the 35th International Conference on Machine Learning
Présenté à:
35th International Conference on Machine Learning, Stockholm, Sweden, July 10 -15, 2018
Année
Jun 08 2018
Mots-clefs:
Laboratoires:




 Notice créée le 2018-06-08, modifiée le 2019-06-19

Fichiers:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)