Optimal discovery with probabilistic expert advice
Optimization and Control
2011-10-26 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.1110.5447,
title = {Optimal discovery with probabilistic expert advice},
author = {Sébastien Bubeck and Damien Ernst and Aurélien Garivier},
journal= {arXiv preprint arXiv:1110.5447},
year = {2011}
}