RiskAverse Stochastic Convex Bandit
[edit]
Proceedings of Machine Learning Research, PMLR 89:3947, 2019.
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 riskaverse. We provide two algorithms to solve this problem. The first one is a descenttype 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 riskaversion in the online convex bandit problem.
Related Material


