AISTATS 2023poster17 citations

Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework

Runzhe Wan, Lin Ge, Rui Song

Abstract

Online learning in large-scale structured bandits is known to be challenging due to the curse of dimensionality. In this paper, we propose a unified meta-learning framework for a wide class of structured bandit problems where the parameter space can be factorized to item-level, which covers many popular tasks. Compared with existing approaches, the proposed solution is both scalable to large systems and robust by utilizing a more flexible model. At the core of this framework is a Bayesian hierarchical model that allows information sharing among items via their features, upon which we design a meta Thompson sampling algorithm. Three representative examples are discussed thoroughly. Theoretical analysis and extensive numerical results both support the usefulness of the proposed method.

BibTeX
@InProceedings{pmlr-v206-wan23a,
  title = 	 {Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework},
  author =       {Wan, Runzhe and Ge, Lin and Song, Rui},
  booktitle = 	 {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1144--1173},
  year = 	 {2023},
  editor = 	 {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem},
  volume = 	 {206},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {25--27 Apr},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v206/wan23a/wan23a.pdf},
  url = 	 {https://proceedings.mlr.press/v206/wan23a.html},
  abstract = 	 {Online learning in large-scale structured bandits is known to be challenging due to the curse of dimensionality. In this paper, we propose a unified meta-learning framework for a wide class of structured bandit problems where the parameter space can be factorized to item-level, which covers many popular tasks. Compared with existing approaches, the proposed solution is both scalable to large systems and robust by utilizing a more flexible model. At the core of this framework is a Bayesian hierarchical model that allows information sharing among items via their features, upon which we design a meta Thompson sampling algorithm. Three representative examples are discussed thoroughly. Theoretical analysis and extensive numerical results both support the usefulness of the proposed method.}
}