Online Passive-Aggressive Algorithms

Abstract

We present a unified view for online classification, regression, and uni- class problems. This view leads to a single algorithmic framework for the three problems. We prove worst case loss bounds for various algorithms for both the realizable case and the non-realizable case. A conversion of our main online algorithm to the setting of batch learning is also dis- cussed. The end result is new algorithms and accompanying loss bounds for the hinge-loss.

Cite

Text

Shalev-shwartz et al. "Online Passive-Aggressive Algorithms." Neural Information Processing Systems, 2003.

Markdown

[Shalev-shwartz et al. "Online Passive-Aggressive Algorithms." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/shalevshwartz2003neurips-online/)

BibTeX

@inproceedings{shalevshwartz2003neurips-online,
  title     = {{Online Passive-Aggressive Algorithms}},
  author    = {Shalev-shwartz, Shai and Crammer, Koby and Dekel, Ofer and Singer, Yoram},
  booktitle = {Neural Information Processing Systems},
  year      = {2003},
  pages     = {1229-1236},
  url       = {https://mlanthology.org/neurips/2003/shalevshwartz2003neurips-online/}
}