| | |
Summary: 1 Bandit View on Noisy Optimization
Jean-Yves Audibert audibert@certis.enpc.fr
Imagine, Universit´e Paris Est; Willow, CNRS/ENS/INRIA
Paris, France
S´ebastien Bubeck sebastien.bubeck@inria.fr
Sequel Project, INRIA Lille - Nord Europe
Lille, France
R´emi Munos remi.munos@inria.fr
Sequel Project, INRIA Lille - Nord Europe
Lille, France
This chapter deals with the problem of making the best use of a finite
number of noisy evaluations to optimize an unknown function. We are
primarily concerned with the case where the function is defined over a finite
set. In this discrete setting, we discuss various objectives for the learner,
from optimizing the allocation of a given budget of evaluations to optimal
stopping time problems with ( , )-PAC guarantees. We also consider the
so-called online optimization framework, where the result of an evaluation is
associated to a reward, and the goal is to maximize the sum of obtained
rewards. In this case, we extend the algorithms to continuous sets and
(weakly) Lipschitzian functions (with respect to a prespecified metric).
|
