ICML 2019oral133 citations

Random Shuffling Beats SGD after Finite Epochs

Jeff Haochen, Suvrit Sra

Abstract

A long-standing problem in stochastic optimization is proving that \rsgd, the without-replacement version of \sgd, converges faster than the usual with-replacement \sgd. Building upon \citep{gurbuzbalaban2015random}, we present the

BibTeX
@InProceedings{pmlr-v97-haochen19a,
  title = 	 {Random Shuffling Beats {SGD} after Finite Epochs},
  author =       {Haochen, Jeff and Sra, Suvrit},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2624--2633},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/haochen19a/haochen19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/haochen19a.html},
  abstract = 	 {A long-standing problem in stochastic optimization is proving that \rsgd, the without-replacement version of \sgd, converges faster than the usual with-replacement \sgd. Building upon \citep{gurbuzbalaban2015random}, we present the