دورية أكاديمية
Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality
العنوان: | Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality |
---|---|
المؤلفون: | Bubeck, Sébastien, Ernst, Damien, Garivier, Aurélien |
المصدر: | Journal of Machine Learning Research, 14, 601-623 (2013-02) |
بيانات النشر: | Microtome Publishing, 2013. |
سنة النشر: | 2013 |
مصطلحات موضوعية: | optimal discovery, probabilistic experts, optimistic algorithm, Good-Turing estimator, UCB, Engineering, computing & technology, Computer science, Ingénierie, informatique & technologie, Sciences informatiques |
الوصف: | 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 on the Good-Turing missing mass estimator. We prove two different regret bounds on the performance of this algorithm under weak assumptions on the probabilistic experts. Under more restrictive hypotheses, we also prove a macroscopic optimality result, comparing the algorithm both with an oracle strategy and with uniform sampling. Finally, we provide numerical experiments illustrating these theoretical findings. |
نوع الوثيقة: | journal article http://purl.org/coar/resource_type/c_6501 article |
اللغة: | English |
Relation: | urn:issn:1532-4435; urn:issn:1533-7928 |
URL الوصول: | https://orbi.uliege.be/handle/2268/143530 |
حقوق: | open access http://purl.org/coar/access_right/c_abf2 info:eu-repo/semantics/openAccess |
رقم الأكسشن: | edsorb.143530 |
قاعدة البيانات: | ORBi |
الوصف غير متاح. |