Bandits attack function optimization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Bandits attack function optimization

Philippe Preux
Rémi Munos
  • Function : Author
  • PersonId : 836863
Michal Valko


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.
Fichier principal
Vignette du fichier
preux2014bandits.pdf (169.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00978637 , version 1 (14-04-2014)


  • HAL Id : hal-00978637 , version 1


Philippe Preux, Rémi Munos, Michal Valko. Bandits attack function optimization. IEEE Congress on Evolutionary Computation, Jul 2014, Beijing, China. ⟨hal-00978637⟩
389 View
556 Download


Gmail Facebook X LinkedIn More