Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds

Shinji Ito, Kei Takemura. Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds. In Gergely Neu, Lorenzo Rosasco, editors, The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, India. Volume 195 of Proceedings of Machine Learning Research, pages 2653-2677, PMLR, 2023. [doi]

@inproceedings{ItoT23-0,
  title = {Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds},
  author = {Shinji Ito and Kei Takemura},
  year = {2023},
  url = {https://proceedings.mlr.press/v195/ito23a.html},
  researchr = {https://researchr.org/publication/ItoT23-0},
  cites = {0},
  citedby = {0},
  pages = {2653-2677},
  booktitle = {The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, India},
  editor = {Gergely Neu and Lorenzo Rosasco},
  volume = {195},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
}