ICML 2016poster164 citations

Contextual Combinatorial Cascading Bandits

Shuai Li, Baoxiang Wang, Shengyu Zhang, Wei Chen

Abstract

We propose the contextual combinatorial cascading bandits, a combinatorial online learning game, where at each time step a learning agent is given a set of contextual information, then selects a list of items, and observes stochastic outcomes of a prefix in the selected items by some stopping criterion. In online recommendation, the stopping criterion might be the first item a user selects; in network routing, the stopping criterion might be the first edge blocked in a path. We consider position discounts in the list order, so that the agent’s reward is discounted depending on the position where the stopping criterion is met. We design a UCB-type algorithm, C^3-UCB, for this problem, prove an n-step regret bound \tildeO(\sqrtn) in the general setting, and give finer analysis for two special cases. Our work generalizes existing studies in several directions, including contextual information, position discounts, and a more general cascading bandit model. Experiments on synthetic and real datasets demonstrate the advantage of involving contextual information and position discounts.

BibTeX
@InProceedings{pmlr-v48-lif16,
  title = 	 {Contextual Combinatorial Cascading Bandits},
  author = 	 {Li, Shuai and Wang, Baoxiang and Zhang, Shengyu and Chen, Wei},
  booktitle = 	 {Proceedings of The 33rd International Conference on Machine Learning},
  pages = 	 {1245--1253},
  year = 	 {2016},
  editor = 	 {Balcan, Maria Florina and Weinberger, Kilian Q.},
  volume = 	 {48},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {New York, New York, USA},
  month = 	 {20--22 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v48/lif16.pdf},
  url = 	 {https://proceedings.mlr.press/v48/lif16.html},
  abstract = 	 {We propose the contextual combinatorial cascading bandits, a combinatorial online learning game, where at each time step a learning agent is given a set of contextual information, then selects a list of items, and observes stochastic outcomes of a prefix in the selected items by some stopping criterion. In online recommendation, the stopping criterion might be the first item a user selects; in network routing, the stopping criterion might be the first edge blocked in a path. We consider position discounts in the list order, so that the agent’s reward is discounted depending on the position where the stopping criterion is met. We design a UCB-type algorithm, C^3-UCB, for this problem, prove an n-step regret bound \tildeO(\sqrtn) in the general setting, and give finer analysis for two special cases. Our work generalizes existing studies in several directions, including contextual information, position discounts, and a more general cascading bandit model. Experiments on synthetic and real datasets demonstrate the advantage of involving contextual information and position discounts.}
}