Open Problem: Model Selection for Contextual Bandits

Abstract

In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.

Cite

Text

Foster et al. "Open Problem: Model Selection for Contextual Bandits." Conference on Learning Theory, 2020.

Markdown

[Foster et al. "Open Problem: Model Selection for Contextual Bandits." Conference on Learning Theory, 2020.](https://mlanthology.org/colt/2020/foster2020colt-open/)

BibTeX

@inproceedings{foster2020colt-open,
  title     = {{Open Problem: Model Selection for Contextual Bandits}},
  author    = {Foster, Dylan J. and Krishnamurthy, Akshay and Luo, Haipeng},
  booktitle = {Conference on Learning Theory},
  year      = {2020},
  pages     = {3842-3846},
  volume    = {125},
  url       = {https://mlanthology.org/colt/2020/foster2020colt-open/}
}