| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Bandits attack function optimization
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.
Cited literature [15 references]
https://hal.inria.fr/hal-00978637
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Monday, April 14, 2014 - 2:32:03 PM
Last modification on : Thursday, January 20, 2022 - 4:17:18 PM
Long-term archiving on: : Monday, July 14, 2014 - 11:45:56 AM
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Monday, April 14, 2014 - 2:32:03 PM
Last modification on : Thursday, January 20, 2022 - 4:17:18 PM
Long-term archiving on: : Monday, July 14, 2014 - 11:45:56 AM
File
preux2014bandits.pdf
Files produced by the author(s)