ML Anthology

On the Universality of Online Mirror Descent

Nati Srebro, Karthik Sridharan, Ambuj Tewari
NeurIPS 2011 pp. 2645-2653
/neurips/2011/srebro2011neurips-universality/

Abstract

We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.

PDF NeurIPS Semantic Scholar

Cite

Text

Srebro et al. "On the Universality of Online Mirror Descent." Neural Information Processing Systems, 2011.

Markdown

[Srebro et al. "On the Universality of Online Mirror Descent." Neural Information Processing Systems, 2011.](https://mlanthology.org/neurips/2011/srebro2011neurips-universality/)

BibTeX

@inproceedings{srebro2011neurips-universality,
  title     = {{On the Universality of Online Mirror Descent}},
  author    = {Srebro, Nati and Sridharan, Karthik and Tewari, Ambuj},
  booktitle = {Neural Information Processing Systems},
  year      = {2011},
  pages     = {2645-2653},
  url       = {https://mlanthology.org/neurips/2011/srebro2011neurips-universality/}
}