Abstract : We consider function optimization as a sequential decision making problem under the budget constraint. Such constraint limits the number of objective function evaluations allowed during the optimization. We consider an algorithm inspired by a continuous version of a multi-armed bandit problem which attacks this optimization problem by solving the tradeoff between exploration (initial quasi-uniform search of the domain) and exploitation (local optimization around the potentially global maxima). We introduce the so-called Simultaneous Optimistic Optimization (SOO), a deterministic algorithm that works by domain partitioning. The benefit of such an approach are the guarantees on the returned solution and the numerical eficiency of the algorithm. We present this machine learning rooted approach to optimization, and provide the empirical assessment of SOO on the CEC'2014 competition on single objective real-parameter numerical optimization testsuite.
Type de document :
Communication dans un congrès
IEEE Congress on Evolutionary Computation, Jul 2014, Beijing, China
https://hal.inria.fr/hal-00978637
Contributeur : Michal Valko
<>
Soumis le : lundi 14 avril 2014 - 14:32:03
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : lundi 14 juillet 2014 - 11:45:56
Philippe Preux, Rémi Munos, Michal Valko. Bandits attack function optimization. IEEE Congress on Evolutionary Computation, Jul 2014, Beijing, China. 〈hal-00978637〉
