From the archives

Empirical Likelihood for Optimistic Algorithms in Dynamic Resource Allocation

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

Context:  Paris X Nanterre

Resume: 

Bandit models, and especially the UCB algorithms, are presented together with statistical challenges they involve: non-asymptotic estimation, self-normalized deviations, Empirical Likelihood.

Slides:  kickoffSPADRO.pdf

Date:  April, 2014

Event url:  ANR SPADRO kick-off meeting

Keywords: