— Many real-world problems are dynamic, requiring an optimization algorithm which is able to continuously track a changing optimum over time. In this paper, we present a stigmerg...
We introduce an efficient algorithm for the problem of online linear optimization in the bandit setting which achieves the optimal O ( T) regret. The setting is a natural general...
In this paper we describe an algorithm to approximately solve a class of semidefinite programs called covering semidefinite programs. This class includes many semidefinite programs...