English

Online Improper Learning with an Approximation Oracle

Machine Learning 2018-04-24 v1 Machine Learning

Abstract

We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per iteration. Furthermore, these algorithms apply to the more general improper learning problems. In the bandit setting, our algorithm also significantly improves the best previously known oracle complexity while maintaining the same regret.

Keywords

Cite

@article{arxiv.1804.07837,
  title  = {Online Improper Learning with an Approximation Oracle},
  author = {Elad Hazan and Wei Hu and Yuanzhi Li and Zhiyuan Li},
  journal= {arXiv preprint arXiv:1804.07837},
  year   = {2018}
}
R2 v1 2026-06-23T01:30:38.937Z