Large Scale Online Learning

Abstract

We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed on- line learning algorithms asymptotically outperform any batch learning algorithm. Both theoretical and experimental evidences are presented.

Cite

Text

Bottou and Cun. "Large Scale Online Learning." Neural Information Processing Systems, 2003.

Markdown

[Bottou and Cun. "Large Scale Online Learning." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/bottou2003neurips-large/)

BibTeX

@inproceedings{bottou2003neurips-large,
  title     = {{Large Scale Online Learning}},
  author    = {Bottou, Léon and Cun, Yann L.},
  booktitle = {Neural Information Processing Systems},
  year      = {2003},
  pages     = {217-224},
  url       = {https://mlanthology.org/neurips/2003/bottou2003neurips-large/}
}