NeurIPS 2016poster44 citations
Optimal Learning for Multi-pass Stochastic Gradient Methods
Abstract
We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. In particular, we consider the square loss and show that for a universal step-size choice, the number of passes acts as a regularization parameter, and optimal finite sample bounds can be achieved by early-stopping. Moreover, we show that larger step-sizes are allowed when considering mini-batches. Our analysis is based on a unifying approach, encompassing both batch and stochastic gradient methods as special cases.
BibTeX
@inproceedings{NIPS2016_fe40fb94,
author = {Lin, Junhong and Rosasco, Lorenzo},
booktitle = {Advances in Neural Information Processing Systems},
editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Optimal Learning for Multi-pass Stochastic Gradient Methods},
url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/fe40fb944ee700392ed51bfe84dd4e3d-Paper.pdf},
volume = {29},
year = {2016}
}