Optimistic optimization of deterministic functions without the knowledge of its smoothness
We consider a global optimization problem of a deterministic function f in a semi-metric space, given a ﬁnite budget of n evaluations. The function f is assumed to be locally smooth (around one of its global maxima) with respect to a semi-metric. We describe two algorithms based on optimistic exploration that use a hierarchical partitioning of the space at all scales. A ﬁrst contribution is an algorithm, DOO, that requires the knowledge of . We report a ﬁnite-sample performance bound in terms of a measure of the quantity of near-optimal states. We then deﬁne a second algorithm, SOO, which does not require the knowledge of the semi-metric under which f is smooth, and whose performance is almost as good as DOO optimally-ﬁtted.
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Rémi Munos|
|Deposited On:||21 February 2012|