English

Risk-Averse Stochastic Convex Bandit

Machine Learning 2018-10-02 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.1810.00737,
  title  = {Risk-Averse Stochastic Convex Bandit},
  author = {Adrian Rivera Cardoso and Huan Xu},
  journal= {arXiv preprint arXiv:1810.00737},
  year   = {2018}
}
R2 v1 2026-06-23T04:24:27.722Z