NeurIPS 2016oral183 citations

Without-Replacement Sampling for Stochastic Gradient Methods

Ohad Shamir

Abstract

Stochastic gradient methods for machine learning and optimization problems are usually analyzed assuming data points are sampled

BibTeX
@inproceedings{NIPS2016_c74d97b0,
 author = {Shamir, Ohad},
 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 = {Without-Replacement Sampling for Stochastic Gradient Methods},
 url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/c74d97b01eae257e44aa9d5bade97baf-Paper.pdf},
 volume = {29},
 year = {2016}
}