%0 Journal Article
%T Optimal discovery with probabilistic expert advice
%A S¨¦bastien Bubeck
%A Damien Ernst
%A Aur¨¦lien Garivier
%J Mathematics
%D 2011
%I arXiv
%X We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and the Good-Turing missing mass estimator. We show that this strategy uniformly attains the optimal discovery rate in a macroscopic limit sense, under some assumptions on the probabilistic experts. We also provide numerical experiments suggesting that this optimal behavior may still hold under weaker assumptions.
%U http://arxiv.org/abs/1110.5447v1