consistent with the statistical properties of the learning algorithm. Our method is generically formulated to cover different …

-called peer group games being non-negative additive games on a permission tree. We provide a polynomial time algorithm for …

We revisit classic algorithmic search and optimization problems from the perspective of competition. Rather than a … single optimizer minimizing expected cost, we consider a zero-sum game in which an optimization problem is presented to two … duels, among others. We give bounds on how often one can beat the classic optimization algorithms in such duels. …