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.