Risk-Averse Stochastic Convex Bandit
arXiv:1810.00737
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.
Cited by in corpus (7)
- Statistical Learning with Conditional Value at Risk
- Learning Bounds for Risk-sensitive Learning
- The Online Saddle Point Problem and Online Convex Optimization with Knapsacks
- Noisy Linear Convergence of Stochastic Gradient Descent for CV@R Statistical Learning under Polyak-Łojasiewicz Conditions
- A Survey of Learning Criteria Going Beyond the Usual Risk
- Learning with CVaR-based feedback under potentially heavy tails
- Risk-Aware MMSE Estimation