Our results show that this initialization method is not only better, in some scenarios, than the uniform sampling used by the current version of irace, but also better than other initialization methods present in other automatic configuration methods. Here, we present an improved initialization method that overcomes these limitations by employing concepts from the design and analysis of computer experiments with branching and nested factors. Although better initialization methods exist in the literature, the mixed-variable (numerical and categorical) nature of typical parameter spaces and the presence of conditional parameters make most of the methods not applicable in practice. By default, irace initializes its search process via uniform sampling of algorithm configurations. Latin hypercube sampling chooses a particular kind of scrambled-order sample consisting of b points from the bd mesh points, and perturbs those points by a small random factor. The irace method is among the most widely used in the literature. Instead, we advocate Latin hypercube sampling, which combines advantages of straightforward integra-tion with those of the traditional Monte Carlo method. Thus, it is advisable to automate this task by using appropriate automatic configuration methods. The configuration of algorithms is a laborious and difficult process.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |