ICML 2018oral56 citations

Online Learning with Abstention

Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Scott Yang

Abstract

We present an extensive study of a key problem in online learning where the learner can opt to abstain from making a prediction, at a certain cost. In the adversarial setting, we show how existing online algorithms and guarantees can be adapted to this problem. In the stochastic setting, we first point out a bias problem that limits the straightforward extension of algorithms such as UCB-N to this context. Next, we give a new algorithm, UCB-GT, that exploits historical data and time-varying feedback graphs. We show that this algorithm benefits from more favorable regret guarantees than a natural extension of UCB-N . We further report the results of a series of experiments demonstrating that UCB-GT largely outperforms that extension of UCB-N, as well as other standard baselines.

BibTeX
@InProceedings{pmlr-v80-cortes18a,
  title = 	 {Online Learning with Abstention},
  author =       {Cortes, Corinna and DeSalvo, Giulia and Gentile, Claudio and Mohri, Mehryar and Yang, Scott},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  pages = 	 {1059--1067},
  year = 	 {2018},
  editor = 	 {Dy, Jennifer and Krause, Andreas},
  volume = 	 {80},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {10--15 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v80/cortes18a/cortes18a.pdf},
  url = 	 {https://proceedings.mlr.press/v80/cortes18a.html},
  abstract = 	 {We present an extensive study of a key problem in online learning where the learner can opt to abstain from making a prediction, at a certain cost. In the adversarial setting, we show how existing online algorithms and guarantees can be adapted to this problem. In the stochastic setting, we first point out a bias problem that limits the straightforward extension of algorithms such as UCB-N to this context. Next, we give a new algorithm, UCB-GT, that exploits historical data and time-varying feedback graphs. We show that this algorithm benefits from more favorable regret guarantees than a natural extension of UCB-N . We further report the results of a series of experiments demonstrating that UCB-GT largely outperforms that extension of UCB-N, as well as other standard baselines.}
}