From the archives

Missing Mass, and Optimal Discovery

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

Context:  ENS Lyon

Resume: 

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.

Slides:  LIP20180514_goodTuring_small.pdf

Date:  May, 2018

Event url:  Laboratoire de l'Informatique du Parallélisme

Keywords: