From the archives

Optimal Discovery with Probabilistic Expert Advice

Historical material. Affiliations, schedules and roles on this page describe their original context.

ConferenceName:  IEEE Conference on Decision and Control

url:  51st IEEE Conference on Decision and Control

Edition Number:  51

Date:  December, 2012

Place:  Hawaï

PageStart:  6 808

PageEnd:  6 812

Authors:  Sébastien BubeckDamien ErnstAurélien Garivier

Abstract: 

Motivated by issues of security analysis for power systems, we analyze a new problem, called 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 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.

Direct link:  available on IEEE Xplore

Arxiv Number:  1110.5447

Keywords: