Risk-Averse Stochastic Convex Bandit

@InProceedings{pmlr-v89-cardoso19a,
  title = 	 {Risk-Averse Stochastic Convex Bandit},
  author =       {Cardoso, Adrian Rivera and Xu, Huan},
  booktitle = 	 {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics},
  pages = 	 {39--47},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Sugiyama, Masashi},
  volume = 	 {89},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {16--18 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v89/cardoso19a/cardoso19a.pdf},
  url = 	 {https://proceedings.mlr.press/v89/cardoso19a.html},
  abstract = 	 {Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse. We provide two algorithms to solve this problem. The first one is a descent-type algorithm which is easy to implement. The second algorithm, which combines the ellipsoid method and a center point device, achieves (almost) optimal regret bounds with respect to the number of rounds. To the best of our knowledge this is the first attempt to address risk-aversion in the online convex bandit problem.}
}