Yishay Mansour

TL;DR: In this paper, the authors extend this theoretical analysis to a multi-test setting, considering both Bernoulli and Gaussian models, and characterize the optimal policy when employees constitute a single group and demonstrate that when the noise levels vary across groups, a fundamental impossibility emerges whereby we cannot administer the same number of tests, subject candidates to the same decision rule, and yet realize the same outcomes in both groups.

TL;DR: In this article, the authors study a mechanism design model in which agents arrive sequentially and each in turn chooses one action from a set of actions with unknown rewards, and characterize the optimal disclosure policy of a planner whose goal is to maximize social welfare.

TL;DR: It is shown how gradient strategies developed to minimize asymptotic regret imply financial trading strategies that yield arbitrage-based bounds for option prices, new and robust in that they do not depend on the continuity of the stock price process, complete markets, or an assumed pricing kernel.

TL;DR: This paper is the first to consider this natural setting of adversarial SSP and obtain sub-linear regret for it, and gives high probability regret bounds of $\widetilde O (\sqrt{K})$ assuming all costs are strictly positive, and $O (K^{3/4})$ for the general case.

TL;DR: Given a black-box access to a Bayesian inference in the classic (adversary-free) setting, the near optimal policy runs in polynomial time in the number of observations and theNumber of possible modification rules.