31 citations · 33 across the 4 of their papers we have counts for
4 papers
Simple regret for infinitely many armed bandits
Alexandra Carpentier, Michal Valko
We consider a stochastic bandit problem with infinitely many arms. In this setting, the learner has no chance of trying all the arms even once and has to dedicate its limited numbe…
Implementable confidence sets in high dimensional regression
Alexandra Carpentier
We consider the setting of linear regression in high dimension. We focus on the problem of constructing adaptive and honest confidence sets for the sparse parameter θ, i.e. we want…
Minimax Number of Strata for Online Stratified Sampling given Noisy Samples
Alexandra Carpentier, Rémi Munos
We consider the problem of online stratified sampling for Monte Carlo integration of a function given a finite budget of noisy evaluations to the function. More precisely we fo…
Bandit Theory meets Compressed Sensing for high dimensional Stochastic Linear Bandit
Alexandra Carpentier, Rémi Munos
We consider a linear stochastic bandit problem where the dimension of the unknown parameter is larger than the sampling budget . In such cases, it is in general impossib…