Risk-Averse Stochastic Convex Bandit

Cardoso, AR; Xu, H

Cardoso, AR (reprint author), Georgia Inst Technol, Atlanta, GA 30332 USA.

22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, 2019; 89 (): 39

Abstract

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision......

Full Text Link